© 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. 5425
    Prev
    Next
    INDEX
    Explanations

    mentions of deadlines

    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
    385
    +0.18
    0.7%
    718
    +0.17
    0.6%
    213
    +0.14
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.18
    0.12
    326
    +0.17
    0.09
    537
    +0.14
    0.06
    Negative Logits
    eland
    -1.09
    ohyd
    -0.92
    ation
    -0.91
    rica
    -0.84
     Chester
    -0.84
    oke
    -0.84
    och
    -0.83
    eller
    -0.82
    izations
    -0.82
    croft
    -0.81
    POSITIVE LOGITS
    nces
    1.00
     mosqu
    0.97
     Skydragon
    0.94
    ¯
    0.89
    matical
    0.88
    ignty
    0.88
     Mulcair
    0.87
    ample
    0.87
    mington
    0.86
    WIN
    0.84
    Activations Density 1.217%

    No Known Activations