© 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
    3. Apollo Research · Taylor · Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning
    5. GPT2-Small
    7. Residual Similar CE E2E Recon
    9. 6-RES_SCEFR-AJT
    11. 14193
    Prev
    Next
    INDEX
    Explanations

    information related to biographical details, career statistics, and organizational affiliations, particularly in the entertainment industry

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    neuronpedia/gpt2-small__res_scefr-ajt/6-res_scefr-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
    326
    +0.21
    0.7%
    339
    +0.19
    0.6%
    285
    +0.14
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    326
    +0.21
    0.08
    415
    +0.19
    0.05
    719
    +0.14
    0.06
    Negative Logits
     Flavoring
    -1.11
    phrine
    -0.98
    xual
    -0.97
    undai
    -0.96
    irie
    -0.92
    heny
    -0.91
     Parade
    -0.88
     Eleven
    -0.86
     Hole
    -0.85
    by
    -0.85
    POSITIVE LOGITS
    dfx
    1.26
    asted
    1.19
    atural
    1.13
    00
    1.12
    ature
    1.10
    ovember
    1.00
    utable
    1.00
    TI
    0.99
    atures
    0.98
    NT
    0.96
    Activations Density 1.135%

    No Known Activations