© 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 Local
    9. 6-RES_SCL-AJT
    11. 36050
    Prev
    Next
    INDEX
    Explanations

    phrases indicating personal reflections or thoughts

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    neuronpedia/gpt2-small__res_scl-ajt/6-res_scl-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
    380
    +0.03
    0.5%
    361
    +0.03
    0.5%
    100
    +0.03
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    107
    +0.03
    0.09
    92
    +0.03
    0.12
    446
    +0.03
    0.12
    Negative Logits
     Pastebin
    -0.20
    chens
    -0.19
     Parenthood
    -0.18
    nant
    -0.18
    Downloadha
    -0.17
    ipers
    -0.17
    uments
    -0.17
    bies
    -0.17
    ials
    -0.16
    endar
    -0.16
    POSITIVE LOGITS
    ttle
    0.21
    hap
    0.19
     regret
    0.19
    haps
    0.18
     luck
    0.18
     venture
    0.18
    phrase
    0.17
    stall
    0.17
    tera
    0.17
    Versions
    0.17
    Activations Density 7.345%

    No Known Activations