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. 34684
    Prev
    Next
    INDEX
    Explanations

    information related to community involvement and volunteer activities

    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
    316
    +0.11
    0.5%
    561
    +0.11
    0.5%
    143
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    640
    +0.11
    0.18
    632
    +0.11
    0.05
    442
    +0.10
    0.06
    Negative Logits
    bage
    -0.81
    bags
    -0.71
    umenthal
    -0.71
    itary
    -0.71
    WithNo
    -0.69
    ilaterally
    -0.69
    ãĥł
    -0.69
    lain
    -0.68
    temp
    -0.67
    jection
    -0.66
    POSITIVE LOGITS
     constitu
    0.93
     ARTICLE
    0.85
     BEL
    0.83
    eka
    0.80
     COUNTY
    0.75
     AGA
    0.73
     CHRIST
    0.72
     STATES
    0.71
     sidx
    0.71
     Pes
    0.70
    Activations Density 5.555%

    No Known Activations