© 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. 31691
    Prev
    Next
    INDEX
    Explanations

    words related to disputes, conflicts, and disagreements

    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
    +0.30
    1.5%
    608
    +0.13
    0.6%
    393
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    608
    +0.30
    0.29
    393
    +0.13
    0.31
    362
    +0.12
    0.17
    Negative Logits
     teasp
    -0.82
    soDeliveryDate
    -0.65
    isSpecialOrderable
    -0.62
    hops
    -0.61
    linger
    -0.60
    earchers
    -0.59
    hes
    -0.59
    ftime
    -0.58
    Hide
    -0.58
    vice
    -0.58
    POSITIVE LOGITS
     how
    0.86
     what
    0.83
     seeing
    0.69
    ¥µ
    0.67
    76561
    0.64
     heights
    0.64
     this
    0.63
    products
    0.63
     whats
    0.62
     why
    0.59
    Activations Density 13.944%

    No Known Activations