© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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 Local
    9. 6-RES_SCL-AJT
    11. 31452
    Prev
    Next
    INDEX
    Explanations

    mentions of senior positions or individuals

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    neuronpedia/gpt2-small__res_scl-ajt/6-res_scl-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
    447
    +0.17
    0.7%
    167
    +0.16
    0.6%
    711
    +0.14
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    616
    +0.17
    0.08
    623
    +0.16
    0.06
    711
    +0.14
    0.04
    Negative Logits
    ellen
    -0.84
    pel
    -0.82
    Ĥİ
    -0.81
    oute
    -0.76
    iky
    -0.76
    doors
    -0.74
    apesh
    -0.71
     tits
    -0.71
    orious
    -0.70
    anism
    -0.69
    POSITIVE LOGITS
    ity
    1.09
    iate
    1.02
     citiz
    0.98
    iates
    0.94
    doms
    0.93
    iating
    0.90
    iaries
    0.89
    itiz
    0.87
    iary
    0.84
     counselor
    0.81
    Activations Density 6.849%

    No Known Activations