© 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 Local
    9. 6-RES_SCL-AJT
    11. 32242
    Prev
    Next
    INDEX
    Explanations

    numerical data related to population, statistics, and quantitative information

    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%
    628
    +0.12
    0.5%
    675
    +0.11
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    260
    +0.17
    0.16
    35
    +0.12
    0.11
    444
    +0.11
    0.10
    Negative Logits
    multipl
    -0.80
    wered
    -0.78
    gran
    -0.78
    ramid
    -0.76
    especially
    -0.75
    intensity
    -0.75
    inducing
    -0.74
    uli
    -0.73
    laden
    -0.72
    unknown
    -0.72
    POSITIVE LOGITS
     cents
    0.96
     percent
    0.90
     anymore
    0.90
    eenth
    0.86
     minutes
    0.83
     feet
    0.82
     Eag
    0.81
     weeks
    0.80
    een
    0.78
     hours
    0.77
    Activations Density 14.156%

    No Known Activations