© 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. 2239
    Prev
    Next
    INDEX
    Explanations

    various forms of the word "conduct"

    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
    361
    +0.17
    0.6%
    288
    +0.16
    0.6%
    570
    +0.16
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.17
    0.09
    361
    +0.16
    0.06
    59
    +0.16
    0.04
    Negative Logits
    cube
    -0.95
     Chimera
    -0.82
    imposed
    -0.80
    ixed
    -0.78
     msec
    -0.77
     Dise
    -0.77
     Nightmares
    -0.76
    Boss
    -0.75
     berth
    -0.75
     Sabha
    -0.74
    POSITIVE LOGITS
    ors
    1.27
    atform
    1.22
    ivity
    1.16
    ORS
    1.09
    ional
    1.06
    uations
    1.04
    onduct
    1.02
    ivist
    1.01
    Īè
    1.01
    ivism
    1.01
    Activations Density 1.324%

    No Known Activations