© 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. 35951
    Prev
    Next
    INDEX
    Explanations

    scientific measurements and data related to nutrition, chemical composition, medical studies, and physical properties

    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
    640
    +0.16
    0.7%
    84
    +0.12
    0.5%
    160
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    640
    +0.16
    0.17
    84
    +0.12
    0.05
    314
    +0.11
    -0.04
    Negative Logits
     Dug
    -0.77
     Carlton
    -0.75
     Answers
    -0.74
     Cantor
    -0.71
     Sovere
    -0.70
     Edgar
    -0.69
     notices
    -0.68
     resemb
    -0.68
     Starr
    -0.68
     tender
    -0.68
    POSITIVE LOGITS
    lbs
    0.97
    each
    0.96
    hr
    0.94
    total
    0.89
    USD
    0.89
    pixel
    0.88
    oz
    0.87
    sq
    0.85
    mol
    0.84
    pair
    0.84
    Activations Density 5.475%

    No Known Activations