Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Apollo Research · Taylor · Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning
    3. GPT2-Small
    4. Residual Similar CE Local
    5. 6-RES_SCL-AJT
    6. 34071
    Prev
    Next
    INDEX
    Explanations

    information related to politics, conflicts, and human rights violations

    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
    87
    +0.44
    4.4%
    266
    +0.34
    3.3%
    447
    +0.20
    2.0%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    87
    +0.44
    -0.22
    64
    +0.34
    -0.43
    447
    +0.20
    0.27
    Negative Logits
     meanwhile
    -0.32
    )?
    -0.29
    swer
    -0.27
     caveats
    -0.27
     partName
    -0.26
    gencies
    -0.25
    doms
    -0.25
    .--
    -0.25
    tions
    -0.23
    )!
    -0.23
    POSITIVE LOGITS
     "â̦
    0.32
     "#
    0.30
     "...
    0.30
     "'
    0.29
     "[
    0.26
     ".
    0.26
     Cipher
    0.26
     ""
    0.24
     transsexual
    0.24
     \"
    0.24
    Activations Density 35.377%

    No Known Activations