© 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. 45671
    Prev
    Next
    INDEX
    Explanations

    keywords related to physical removal or extraction

    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
    +0.33
    1.4%
    565
    +0.12
    0.5%
    57
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    59
    +0.33
    0.09
    566
    +0.12
    0.11
    761
    +0.12
    0.10
    Negative Logits
    ingham
    -0.76
     Rate
    -0.72
    matic
    -0.71
    soType
    -0.70
    gregation
    -0.69
     msec
    -0.69
    acebook
    -0.68
    Activ
    -0.68
    zag
    -0.68
     Winds
    -0.68
    POSITIVE LOGITS
    uder
    0.91
     unnecessary
    0.88
     limbs
    0.82
     foreskin
    0.81
     duplicate
    0.81
    leted
    0.79
     redundant
    0.78
    brid
    0.77
    uters
    0.76
    cliffe
    0.76
    Activations Density 12.716%

    No Known Activations