© 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 24576
    9. 8-RES_FS24576-JB
    11. 1770
    Prev
    Next
    INDEX
    Explanations

    references to advancement or progress

    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
    373
    +0.10
    0.5%
    125
    +0.10
    0.5%
    39
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    125
    +0.10
    0.01
    62
    +0.10
    0.01
    39
    +0.10
    0.01
    Negative Logits
    BALL
    -0.64
    =]
    -0.61
    atis
    -0.61
    Rus
    -0.60
    »Ĵ
    -0.58
    mology
    -0.57
     DRAG
    -0.56
     Munich
    -0.56
     Audi
    -0.56
     Fields
    -0.55
    POSITIVE LOGITS
     appearances
    0.93
     pace
    0.80
     footing
    0.72
    earances
    0.71
    endra
    0.68
    standing
    0.68
    ouver
    0.67
    ency
    0.66
    earance
    0.66
    dating
    0.65
    Activations Density 0.021%

    No Known Activations