© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 910
    Prev
    Next
    INDEX
    Explanations

    phrases indicating missed opportunities or alternate actions that could have been taken

    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
    320
    +0.13
    0.7%
    393
    +0.09
    0.4%
    280
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    320
    +0.13
    0.04
    7
    +0.09
    0.04
    277
    +0.09
    0.03
    Negative Logits
    vich
    -0.62
    bert
    -0.61
     paycheck
    -0.56
    baugh
    -0.56
     Blitz
    -0.55
    Äĩ
    -0.54
     Lv
    -0.53
    stown
    -0.52
    pour
    -0.52
    malink
    -0.50
    POSITIVE LOGITS
    ħĭ
    0.72
     gotten
    0.70
     been
    0.67
     feas
    0.66
     salv
    0.66
    ivably
    0.65
    »Ĵ
    0.65
    ©¶æ
    0.63
     afforded
    0.61
     accommod
    0.61
    Activations Density 0.320%

    No Known Activations