© 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. 9687
    Prev
    Next
    INDEX
    Explanations

    dates or years

    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
    481
    +0.16
    0.7%
    430
    +0.14
    0.6%
    633
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    146
    +0.16
    0.07
    430
    +0.14
    0.07
    306
    +0.10
    0.06
    Negative Logits
    amins
    -0.65
    atio
    -0.65
     genus
    -0.59
    elong
    -0.57
    icons
    -0.56
     smugglers
    -0.55
     emulation
    -0.55
    axis
    -0.54
    ãģį
    -0.53
    aghetti
    -0.53
    POSITIVE LOGITS
     onwards
    0.78
     RELEASE
    0.74
     partName
    0.69
    20439
    0.68
     GMT
    0.67
    £ı
    0.67
     Became
    0.66
    âĸĪâĸĪ
    0.65
    displayText
    0.65
    lished
    0.64
    Activations Density 0.179%

    No Known Activations