© 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. 31649
    Prev
    Next
    INDEX
    Explanations

    descriptions of traditional ceremonies and rituals

    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
    +0.20
    1.2%
    163
    +0.09
    0.5%
    476
    +0.09
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    163
    +0.20
    0.11
    393
    +0.09
    0.25
    237
    +0.09
    0.07
    Negative Logits
    ubi
    -0.57
    aline
    -0.53
    uel
    -0.50
    ees
    -0.47
    clus
    -0.46
    bek
    -0.45
     Dull
    -0.44
    alin
    -0.43
    elve
    -0.43
    ati
    -0.43
    POSITIVE LOGITS
     imaginable
    0.79
     conceivable
    0.68
    THING
    0.65
    body
    0.59
    WHERE
    0.54
    STD
    0.53
    WAYS
    0.53
     partName
    0.50
    VICE
    0.49
     ILCS
    0.49
    Activations Density 10.231%

    No Known Activations