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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 33208
    Prev
    Next
    INDEX
    Explanations

    comparisons related to socioeconomic status

    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
    +0.15
    0.7%
    643
    +0.09
    0.4%
    4
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    762
    +0.15
    0.17
    119
    +0.09
    0.11
    351
    +0.09
    0.05
    Negative Logits
    forestation
    -0.78
    Gall
    -0.69
    scientific
    -0.69
    binding
    -0.69
    ART
    -0.68
    FK
    -0.68
    Saint
    -0.67
    ELD
    -0.65
    aye
    -0.65
    aram
    -0.64
    POSITIVE LOGITS
     financially
    0.85
     knowing
    0.73
     bets
    0.73
    amia
    0.72
     investing
    0.70
    looking
    0.68
     than
    0.68
     looking
    0.65
     watching
    0.65
    ners
    0.63
    Activations Density 8.219%

    No Known Activations