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. 45598
    Prev
    Next
    INDEX
    Explanations

    interactions between individuals

    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
    +0.32
    1.3%
    416
    +0.13
    0.5%
    492
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    762
    +0.32
    0.16
    506
    +0.13
    0.07
    553
    +0.12
    0.06
    Negative Logits
    ģ
    -0.76
     Variety
    -0.71
    °
    -0.68
    QL
    -0.68
    Ń·
    -0.67
    cit
    -0.66
    uci
    -0.66
    @#&
    -0.65
     turnaround
    -0.65
     Noon
    -0.63
    POSITIVE LOGITS
    worldly
    1.40
    selves
    1.02
    wise
    0.82
    stretched
    0.76
     mate
    0.75
    inant
    0.73
     mutually
    0.72
     equally
    0.71
    friend
    0.71
    bage
    0.71
    Activations Density 12.209%

    No Known Activations