© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Apollo Research · Taylor · Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning
    5. GPT2-Small
    7. Residual Similar CE E2E Recon
    9. 6-RES_SCEFR-AJT
    11. 2092
    Prev
    Next
    INDEX
    Explanations

    technical issues or problems related to software, technology, or physical products

    oai_token-act-pair · gpt-3.5-turbo

    words denoting difficulties or issues, often using the word "problem"

    oai_token-act-pair · gpt-3.5-turboTriggered by @jordan
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    neuronpedia/gpt2-small__res_scefr-ajt/6-res_scefr-ajt
    Prompts (Dashboard)
    12,288 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    46,080
    Data Type
    torch.float32
    Hook Point
    blocks.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    apollo-research/Skylion007-openwebtext-tokenizer-gpt2
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    286
    +0.06
    0.5%
    84
    +0.06
    0.5%
    219
    +0.06
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    195
    +0.06
    0.02
    357
    +0.06
    0.03
    27
    +0.06
    0.03
    Negative Logits
    ©¶æ
    -0.62
    usters
    -0.47
    illy
    -0.46
    ignty
    -0.45
    emouth
    -0.45
    apes
    -0.42
    aping
    -0.41
    ieties
    -0.39
    kee
    -0.38
    otes
    -0.38
    POSITIVE LOGITS
     TEXT
    0.48
     Fore
    0.35
     reper
    0.35
     looting
    0.34
     reprint
    0.34
     haunt
    0.34
     .)
    0.34
     Yugoslav
    0.34
    acebook
    0.34
     retrieving
    0.33
    Activations Density 0.209%

    No Known Activations