© 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. 10322
    Prev
    Next
    INDEX
    Explanations

    numerical estimations and figures

    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
    101
    +0.15
    0.7%
    653
    +0.11
    0.5%
    622
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    101
    +0.15
    0.04
    724
    +0.11
    0.03
    653
    +0.10
    0.03
    Negative Logits
    feeding
    -0.87
    ĪĴ
    -0.78
    Interstitial
    -0.77
    matter
    -0.76
    woods
    -0.76
    oard
    -0.73
    interrupted
    -0.69
    ierre
    -0.69
    nered
    -0.69
    bara
    -0.69
    POSITIVE LOGITS
     estimates
    1.02
     estimate
    0.98
     estimated
    0.87
    imate
    0.84
     approximate
    0.83
     estimating
    0.82
     number
    0.81
     elapsed
    0.79
     distances
    0.79
     probabilities
    0.77
    Activations Density 0.097%

    No Known Activations