© 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. 35501
    Prev
    Next
    INDEX
    Explanations

    descriptions of physical actions and sequences related to physical surroundings

    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
    +0.13
    0.6%
    273
    +0.09
    0.4%
    201
    +0.08
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    393
    +0.13
    0.27
    526
    +0.09
    -0.07
    362
    +0.08
    0.13
    Negative Logits
    trip
    -0.62
    essee
    -0.60
    ļéĨĴ
    -0.60
    cliffe
    -0.59
    alty
    -0.57
    apest
    -0.56
    essors
    -0.56
    ryu
    -0.56
    ellar
    -0.56
    istani
    -0.55
    POSITIVE LOGITS
    wards
    0.89
     hither
    0.75
    Downloadha
    0.70
     mete
    0.69
     ecstasy
    0.68
     corners
    0.65
     uncontroll
    0.64
     promul
    0.61
     seams
    0.61
     bushes
    0.61
    Activations Density 11.846%

    No Known Activations