© 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. 1373
    Prev
    Next
    INDEX
    Explanations

    sentences with grammar issues that need improvement

    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
    690
    +0.11
    0.5%
    79
    +0.09
    0.4%
    762
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    665
    +0.11
    0.10
    570
    +0.09
    0.02
    690
    +0.09
    0.07
    Negative Logits
    ©¶æ¥µ
    -0.64
    joice
    -0.64
    ilings
    -0.62
    é¾į
    -0.61
    ourses
    -0.61
    çīĪ
    -0.60
    veland
    -0.60
    avid
    -0.59
    adelphia
    -0.59
    ctors
    -0.58
    POSITIVE LOGITS
     itself
    1.11
     raining
    1.11
     corro
    0.80
     decay
    0.78
     ITS
    0.74
     dissip
    0.74
     belonged
    0.72
     its
    0.71
     belongs
    0.69
     malfunction
    0.68
    Activations Density 1.207%

    No Known Activations