© 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. 341
    Prev
    Next
    INDEX
    Explanations

    sequences of numbers separated by a period such as in percentages or measurements

    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
    87
    +0.23
    1.2%
    481
    +0.17
    0.9%
    642
    +0.14
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    87
    +0.23
    -0.05
    756
    +0.17
    -0.06
    393
    +0.14
    0.14
    Negative Logits
     marrow
    -0.53
     Gaal
    -0.45
     aud
    -0.43
     Tud
    -0.42
     Gael
    -0.42
    Ã
    -0.42
    cend
    -0.42
     âĢİ
    -0.41
     Cu
    -0.41
    wav
    -0.41
    POSITIVE LOGITS
    etheless
    0.59
    ardless
    0.57
     conflic
    0.57
    FORE
    0.52
    ucer
    0.51
    ģ«
    0.51
    Ĭ±
    0.50
     tradem
    0.50
    è¦ļéĨĴ
    0.49
    ãģ®ç
    0.49
    Activations Density 3.559%

    No Known Activations