© 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 12288
    9. 8-RES_FS12288-JB
    11. 10234
    Prev
    Next
    INDEX
    Explanations

    positive and negative societal or personal achievements or status

    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
    287
    +0.11
    0.5%
    322
    +0.10
    0.4%
    362
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    362
    +0.11
    0.04
    16
    +0.10
    0.03
    172
    +0.09
    0.03
    Negative Logits
    Cause
    -0.66
    ary
    -0.66
     embodiments
    -0.64
    eral
    -0.64
    ista
    -0.63
    soever
    -0.62
    cause
    -0.60
     Ruk
    -0.59
    workers
    -0.58
    acea
    -0.58
    POSITIVE LOGITS
     charts
    0.91
     hill
    0.90
     earners
    0.87
     stairs
    0.82
     notch
    0.81
     heap
    0.79
     nowhere
    0.79
     totem
    0.78
     standings
    0.76
     hierarchy
    0.76
    Activations Density 0.166%

    No Known Activations