© 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 Local
    9. 6-RES_SCL-AJT
    11. 40383
    Prev
    Next
    INDEX
    Explanations

    explicit and graphic language

    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
    447
    +0.17
    0.7%
    48
    +0.13
    0.5%
    306
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    48
    +0.17
    0.11
    640
    +0.13
    0.18
    316
    +0.12
    0.07
    Negative Logits
    BIL
    -0.92
    anu
    -0.89
    endant
    -0.89
    Msg
    -0.84
    Folder
    -0.84
    ilus
    -0.83
     seiz
    -0.83
    inel
    -0.82
    laus
    -0.82
    NetMessage
    -0.81
    POSITIVE LOGITS
     kidding
    1.08
    huge
    0.95
    holes
    0.91
     fucking
    0.88
     idiot
    0.87
     idiots
    0.87
     prick
    0.87
     retard
    0.84
     fuck
    0.82
     tease
    0.81
    Activations Density 7.570%

    No Known Activations