© 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 49152
    9. 8-RES_FS49152-JB
    11. 26564
    Prev
    Next
    INDEX
    Explanations

    measurements and dimensions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs49152-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_49152
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    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
    185
    +0.10
    0.5%
    497
    +0.10
    0.5%
    208
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    507
    +0.10
    0.02
    326
    +0.10
    0.01
    586
    +0.10
    0.01
    Negative Logits
    heit
    -0.79
    vik
    -0.67
     Buckley
    -0.65
    swers
    -0.64
     abiding
    -0.61
    FUL
    -0.61
     involuntary
    -0.60
    liest
    -0.59
    anke
    -0.58
     Vi
    -0.58
    POSITIVE LOGITS
     pixels
    1.00
    px
    0.98
     inches
    0.98
     centimeters
    0.97
    cm
    0.96
     cm
    0.96
     inch
    0.92
     magnification
    0.86
    pixel
    0.85
     meters
    0.83
    Activations Density 0.031%

    No Known Activations