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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 13193
    Prev
    Next
    INDEX
    Explanations

    references to numerical values and IDs

    oai_token-act-pair · gpt-3.5-turbo
    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
    42
    +0.02
    0.4%
    426
    +0.02
    0.4%
    600
    +0.01
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    639
    +0.02
    0.01
    406
    +0.02
    0.01
    373
    +0.01
    -0.00
    Negative Logits
     Australians
    -0.14
     BC
    -0.13
     Australian
    -0.13
     Canadians
    -0.13
     Carib
    -0.13
     Canadian
    -0.12
     Advertisement
    -0.12
     Brit
    -0.11
     BCE
    -0.11
     Sunrise
    -0.11
    POSITIVE LOGITS
    anan
    0.16
    »Ĵ
    0.15
    ©¶æ
    0.15
    aan
    0.15
     encount
    0.14
    rek
    0.14
    nih
    0.13
    achus
    0.13
    LER
    0.13
    urg
    0.13
    Activations Density 0.011%

    No Known Activations