© 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 EvalsExportsAPI 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. 12810
    Prev
    Next
    INDEX
    Explanations

    locations or events related to clowns

    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
    728
    +0.16
    0.6%
    99
    +0.14
    0.5%
    344
    +0.14
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    326
    +0.16
    0.10
    99
    +0.14
    0.07
    288
    +0.14
    0.10
    Negative Logits
    master
    -1.10
    quickShipAvailable
    -1.08
    masters
    -1.08
    DERR
    -1.04
    clinton
    -0.94
    enegger
    -0.93
    ARDS
    -0.92
    breaking
    -0.90
    Disney
    -0.90
    urst
    -0.90
    POSITIVE LOGITS
    asure
    1.34
    asures
    1.23
    teness
    1.22
    thora
    1.14
    fters
    1.09
    asuring
    1.08
    asers
    1.06
    etary
    1.06
    ptic
    1.03
    MENTS
    1.03
    Activations Density 1.500%

    No Known Activations