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 L0 E2E Recon
    5. 2-RES_SLEFR-AJT
    6. 9862
    Prev
    Next
    INDEX
    Explanations

    Names of people, organizations, or legal entities. Frequently, these names are associated with legal or governmental actions or investigations.

    eleuther_acts_top20 · gemini-1.5-flashTriggered by @johnny

    references to Eric Holder and related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    neuronpedia/gpt2-small__res_slefr-ajt/2-res_slefr-ajt
    Prompts (Dashboard)
    12,288 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    46,080
    Data Type
    torch.float32
    Hook Point
    blocks.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    apollo-research/Skylion007-openwebtext-tokenizer-gpt2
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    35
    +0.15
    0.6%
    253
    +0.11
    0.4%
    718
    +0.11
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    35
    +0.15
    0.02
    762
    +0.11
    0.02
    146
    +0.11
    0.02
    Negative Logits
    oster
    -0.73
    LV
    -0.72
    resh
    -0.72
    opic
    -0.70
     salon
    -0.70
    Bay
    -0.70
    Gaza
    -0.70
    Live
    -0.70
    ologist
    -0.69
    chrom
    -0.69
    POSITIVE LOGITS
    owship
    0.89
     recip
    0.83
     concess
    0.82
    artz
    0.79
    thood
    0.79
     holder
    0.78
     horizont
    0.78
    ocument
    0.77
    milo
    0.77
     Holder
    0.76
    Activations Density 0.043%

    No Known Activations