© 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. 11052
    Prev
    Next
    INDEX
    Explanations

    verbs related to physical actions or movements

    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
    665
    +0.15
    0.6%
    70
    +0.12
    0.5%
    664
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    665
    +0.15
    0.22
    70
    +0.12
    0.17
    184
    +0.12
    0.10
    Negative Logits
    è¦ļéĨĴ
    -0.80
     guiActiveUnfocused
    -0.77
    ascus
    -0.73
    hess
    -0.72
    acteria
    -0.71
    hal
    -0.71
    culus
    -0.69
    Downloadha
    -0.69
    tymology
    -0.66
    arrow
    -0.66
    POSITIVE LOGITS
     him
    0.82
    ingly
    0.78
     ANY
    0.78
     whoever
    0.74
     whatever
    0.74
     them
    0.73
     anytime
    0.73
    fully
    0.72
     tomorrow
    0.71
    ELY
    0.71
    Activations Density 3.899%

    No Known Activations