© 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. 7332
    Prev
    Next
    INDEX
    Explanations

    words related to physical actions or physical interactions

    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
    373
    +0.04
    0.6%
    28
    +0.04
    0.5%
    616
    +0.04
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    526
    +0.04
    0.01
    326
    +0.04
    0.04
    251
    +0.04
    0.03
    Negative Logits
    ensions
    -0.29
    idian
    -0.27
    downs
    -0.27
    ension
    -0.26
    OTOS
    -0.25
     Machina
    -0.25
    izers
    -0.24
    isms
    -0.24
    isable
    -0.24
     NCT
    -0.24
    POSITIVE LOGITS
    erd
    0.26
    loo
    0.25
    efully
    0.24
     fav
    0.24
    proxy
    0.23
    ctor
    0.23
    atered
    0.22
    gypt
    0.22
     webs
    0.22
     dinosaurs
    0.22
    Activations Density 0.189%

    No Known Activations