© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Feature Splitting for GPT2-Small
    5. GPT2-Small
    7. Residual Feature Splitting 768
    9. 8-RES_FS768-JB
    11. 728
    Prev
    Next
    INDEX
    Explanations

    words related to criticism or negative judgment

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs768-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_768
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    768
    Data Type
    torch.float32
    Hook Point
    blocks.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    99
    +0.16
    0.7%
    438
    +0.14
    0.6%
    62
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    659
    +0.16
    0.14
    99
    +0.14
    0.11
    232
    +0.10
    0.10
    Negative Logits
    uate
    -0.94
    uated
    -0.70
     inhibition
    -0.66
     susceptibility
    -0.65
     sucker
    -0.65
    uations
    -0.65
     unpre
    -0.64
    inates
    -0.63
    arial
    -0.62
     gratification
    -0.60
    POSITIVE LOGITS
    restling
    1.27
    nesday
    1.24
    ITNESS
    1.20
    elcome
    1.18
    atts
    1.14
    edge
    1.14
    orthy
    1.13
    ashington
    1.13
    esome
    1.11
    isdom
    1.10
    Activations Density 3.570%

    No Known Activations