© 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. 36337
    Prev
    Next
    INDEX
    Explanations

    references to revenge or retaliatory actions

    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
    +0.27
    1.1%
    431
    +0.13
    0.6%
    288
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    703
    +0.27
    0.09
    526
    +0.13
    -0.13
    393
    +0.12
    0.29
    Negative Logits
    baum
    -0.78
     livest
    -0.76
    ographics
    -0.75
    estone
    -0.71
    âĢ¢âĢ¢
    -0.70
    osite
    -0.70
    66666666
    -0.69
    quart
    -0.68
    zyme
    -0.68
    umbers
    -0.67
    POSITIVE LOGITS
     revenge
    1.18
     vengeance
    1.13
     retribution
    1.08
     retaliation
    0.96
     aven
    0.93
     against
    0.93
    venge
    0.91
     retali
    0.90
     reven
    0.85
     repr
    0.83
    Activations Density 16.017%

    No Known Activations