© 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. 7371
    Prev
    Next
    INDEX
    Explanations

    sentiments and actions related to unity and support among individuals and communities

    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
    288
    +0.17
    0.8%
    523
    +0.12
    0.6%
    445
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    445
    +0.17
    0.01
    288
    +0.12
    0.01
    523
    +0.12
    0.01
    Negative Logits
    kj
    -0.78
    stall
    -0.74
    gran
    -0.73
    rey
    -0.71
    nos
    -0.70
    erion
    -0.70
    fect
    -0.68
    eger
    -0.67
    corn
    -0.67
    riber
    -0.66
    POSITIVE LOGITS
    arity
    1.25
     solidarity
    1.04
     towards
    0.85
     gesture
    0.81
     vigil
    0.81
     Towards
    0.78
     toward
    0.77
     anthem
    0.73
     against
    0.70
    mates
    0.68
    Activations Density 0.016%

    No Known Activations