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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 34393
    Prev
    Next
    INDEX
    Explanations

    references to British individuals, locations, and political parties

    oai_token-act-pair · gpt-3.5-turbo

    words related to British nationality or culture

    oai_token-act-pair · gpt-3.5-turboTriggered by @danbraun
    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
    314
    +0.14
    0.6%
    420
    +0.14
    0.6%
    587
    +0.13
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    659
    +0.14
    0.13
    314
    +0.14
    -0.02
    232
    +0.13
    0.10
    Negative Logits
     chambers
    -0.78
     contraceptives
    -0.78
    ATA
    -0.76
     Referred
    -0.75
    isSpecialOrderable
    -0.74
    TPPStreamerBot
    -0.72
     Authorization
    -0.71
    /+
    -0.71
     contraceptive
    -0.70
     STATS
    -0.70
    POSITIVE LOGITS
    ois
    1.04
    istani
    1.01
    ophone
    0.96
    oise
    0.96
    Rail
    0.93
    anu
    0.91
    ney
    0.90
    tex
    0.90
    spe
    0.89
     Hume
    0.88
    Activations Density 7.328%

    No Known Activations