© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 33832
    Prev
    Next
    INDEX
    Explanations

    statements or declarations made within an official report

    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
    +0.22
    1.0%
    481
    +0.17
    0.8%
    234
    +0.15
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    679
    +0.22
    0.25
    452
    +0.17
    0.10
    640
    +0.15
    0.23
    Negative Logits
    Occup
    -0.66
    pron
    -0.65
    grain
    -0.64
     Maker
    -0.64
    Pont
    -0.63
    ben
    -0.63
    brook
    -0.62
    acqu
    -0.62
     spectator
    -0.61
    patch
    -0.61
    POSITIVE LOGITS
     titled
    0.74
     furthermore
    0.70
     summar
    0.70
     scathing
    0.70
     quoting
    0.69
     omin
    0.69
     comprises
    0.68
     seq
    0.66
     authors
    0.66
     convinc
    0.65
    Activations Density 10.210%

    No Known Activations