© 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
    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. 40453
    Prev
    Next
    INDEX
    Explanations

    ZIP codes and related terms

    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
    516
    +0.11
    0.5%
    113
    +0.10
    0.5%
    566
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    526
    +0.11
    -0.05
    516
    +0.10
    0.06
    608
    +0.10
    0.12
    Negative Logits
    ership
    -0.77
    raising
    -0.76
    ¯¯
    -0.75
    nesota
    -0.72
    ivia
    -0.72
    igmatic
    -0.71
    swer
    -0.71
    nces
    -0.71
    ¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯
    -0.69
    naissance
    -0.69
    POSITIVE LOGITS
     zip
    0.86
    Zip
    0.82
     Zip
    0.78
    zip
    0.71
     sum
    0.71
    INO
    0.69
     compress
    0.68
    PER
    0.67
     archive
    0.66
    ijn
    0.66
    Activations Density 6.509%

    No Known Activations