© 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 E2E Recon
    9. 6-RES_SCEFR-AJT
    11. 10813
    Prev
    Next
    INDEX
    Explanations

    words related to unleashing or releasing energy or forces

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    neuronpedia/gpt2-small__res_scefr-ajt/6-res_scefr-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
    288
    +0.16
    0.7%
    271
    +0.14
    0.6%
    761
    +0.13
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    271
    +0.16
    0.05
    288
    +0.14
    0.07
    761
    +0.13
    0.05
    Negative Logits
     Represent
    -0.82
    sem
    -0.80
    atem
    -0.78
    ĸļ
    -0.75
    externalActionCode
    -0.75
    iasis
    -0.75
     Matter
    -0.74
    journal
    -0.74
     Mond
    -0.73
    cean
    -0.72
    POSITIVE LOGITS
    ãĥ¤
    1.03
     unleashed
    0.95
     unle
    0.91
    quished
    0.84
    ricane
    0.77
    amaz
    0.76
    storm
    0.73
    ILLE
    0.72
    ZZ
    0.71
    arded
    0.71
    Activations Density 0.685%

    No Known Activations