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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Feature Splitting for GPT2-Small
    5. GPT2-Small
    7. Residual Feature Splitting 24576
    9. 8-RES_FS24576-JB
    11. 8889
    Prev
    Next
    INDEX
    Explanations

    words related to feelings of contempt or disrespect towards authority or specific groups

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs24576-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_24576
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    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
    624
    +0.14
    0.6%
    289
    +0.13
    0.6%
    161
    +0.13
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    161
    +0.14
    0.02
    624
    +0.13
    0.02
    301
    +0.13
    0.02
    Negative Logits
    ramid
    -0.69
     hemor
    -0.68
     Lans
    -0.65
    NetMessage
    -0.64
     encyclopedia
    -0.63
     toget
    -0.61
    akeru
    -0.60
     reconstruction
    -0.60
     stabilization
    -0.60
     advoc
    -0.60
    POSITIVE LOGITS
    uously
    1.55
    uous
    1.52
    fully
    1.20
    ible
    1.18
    ibly
    1.09
    ful
    1.04
    ateurs
    1.02
    ardless
    1.01
    urous
    1.00
    orable
    0.99
    Activations Density 0.041%

    No Known Activations