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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 5525
    Prev
    Next
    INDEX
    Explanations

    information related to legal matters and court cases

    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
    345
    +0.03
    0.6%
    347
    +0.02
    0.4%
    167
    +0.02
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    232
    +0.03
    0.03
    525
    +0.02
    0.02
    421
    +0.02
    0.02
    Negative Logits
     amplified
    -0.15
     TEXT
    -0.15
     Parenthood
    -0.15
     toget
    -0.15
     partName
    -0.15
    xual
    -0.15
     helic
    -0.14
    ĪĴ
    -0.14
     "@
    -0.14
    ktop
    -0.14
    POSITIVE LOGITS
    ron
    0.17
    rick
    0.16
    leton
    0.15
    luck
    0.15
    itus
    0.15
    Safe
    0.15
    minster
    0.15
    dan
    0.14
    emark
    0.14
    lean
    0.14
    Activations Density 0.113%

    No Known Activations