© 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. 888
    Prev
    Next
    INDEX
    Explanations

    names of sports teams

    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
    642
    +0.12
    0.5%
    152
    +0.10
    0.5%
    493
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    642
    +0.12
    0.02
    493
    +0.10
    0.03
    152
    +0.10
    0.03
    Negative Logits
    xual
    -0.82
    rav
    -0.70
    avorite
    -0.69
    URR
    -0.67
    lectic
    -0.66
     Sawyer
    -0.64
    atton
    -0.63
    orst
    -0.61
    cake
    -0.60
     DRAG
    -0.59
    POSITIVE LOGITS
     Madrid
    1.35
    istically
    1.31
    ignment
    1.23
    istic
    1.22
     Estate
    1.21
     estate
    1.12
    estate
    1.07
    idad
    1.06
    ization
    1.06
    tek
    1.04
    Activations Density 0.040%

    No Known Activations