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

    Neuronpedia

    Jacobian LensNEW
    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. 7732
    Prev
    Next
    INDEX
    Explanations

    sentences discussing factors or contributions to a situation

    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
    403
    +0.13
    0.6%
    691
    +0.12
    0.6%
    259
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    403
    +0.13
    0.04
    691
    +0.12
    0.04
    608
    +0.12
    0.04
    Negative Logits
    alach
    -0.71
    lance
    -0.69
     Memor
    -0.67
    atography
    -0.67
    ARE
    -0.66
    efer
    -0.64
    intend
    -0.63
    byter
    -0.63
    heit
    -0.63
    Bus
    -0.63
    POSITIVE LOGITS
     why
    0.97
     motivating
    0.92
     determining
    0.91
     favoring
    0.87
     susceptibility
    0.85
     influencing
    0.81
     exacerb
    0.79
     triggering
    0.78
     factors
    0.78
    why
    0.78
    Activations Density 0.182%

    No Known Activations