© 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. 45880
    Prev
    Next
    INDEX
    Explanations

    references to government programs or political figures

    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
    153
    +0.05
    0.5%
    297
    +0.05
    0.5%
    505
    +0.05
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    264
    +0.05
    0.05
    147
    +0.05
    0.07
    567
    +0.05
    0.08
    Negative Logits
    src
    -0.40
    ripp
    -0.36
    rez
    -0.35
    wp
    -0.35
    bern
    -0.35
    uga
    -0.35
    uku
    -0.34
    whe
    -0.34
    inventoryQuantity
    -0.34
    idges
    -0.34
    POSITIVE LOGITS
     visa
    0.44
     Visa
    0.41
     visas
    0.41
     Assistance
    0.38
     designation
    0.37
     Authorization
    0.37
     Disability
    0.36
     Loans
    0.36
     Identification
    0.36
     authorization
    0.35
    Activations Density 21.191%

    No Known Activations