© 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 EvalsExportsinterp-engineNEWAPI 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. 10984
    Prev
    Next
    INDEX
    Explanations

    names of well-known individuals

    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
    203
    +0.14
    0.5%
    232
    +0.13
    0.5%
    379
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    232
    +0.14
    0.05
    406
    +0.13
    0.05
    284
    +0.12
    0.05
    Negative Logits
     Lauder
    -0.90
    blance
    -0.88
    URA
    -0.79
     variance
    -0.79
     istg
    -0.78
    Timeout
    -0.74
    piece
    -0.74
    vp
    -0.74
     unfocusedRange
    -0.73
    mble
    -0.73
    POSITIVE LOGITS
    hemy
    1.24
    eworthy
    1.10
    pedia
    1.09
    aneers
    0.98
    idi
    0.94
    leck
    0.92
    hari
    0.92
    ucha
    0.91
    etooth
    0.90
    acan
    0.90
    Activations Density 0.536%

    No Known Activations