© 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
    2. Joseph Bloom · Feature Splitting for GPT2-Small
    3. GPT2-Small
    4. Residual Feature Splitting 12288
    5. 8-RES_FS12288-JB
    6. 364
    Prev
    Next
    INDEX
    Explanations

    foreign language text

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs12288-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_12288
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    12,288
    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
    160
    +0.10
    0.5%
    229
    +0.09
    0.4%
    373
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    229
    +0.10
    0.02
    284
    +0.09
    0.01
    609
    +0.09
    0.01
    Negative Logits
     delegation
    -0.76
    creen
    -0.73
     disproportion
    -0.70
     Jericho
    -0.68
     compromise
    -0.67
     destro
    -0.65
     braces
    -0.65
     potatoes
    -0.65
     Clarkson
    -0.63
     booths
    -0.63
    POSITIVE LOGITS
    ________
    1.04
    ________________________________________________________________
    1.04
    iced
    1.03
    ________________
    1.02
    ********
    1.00
    Ñģ
    1.00
    _____
    0.97
    î
    0.96
    iph
    0.95
    --------------
    0.95
    Activations Density 0.038%

    No Known Activations