© 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
    2. Joseph Bloom · Feature Splitting for GPT2-Small
    3. GPT2-Small
    4. Residual Feature Splitting 24576
    5. 8-RES_FS24576-JB
    6. 9336
    Prev
    Next
    INDEX
    Explanations

    direct speech verbs

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs24576-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_24576
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    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
    274
    +0.11
    0.5%
    679
    +0.10
    0.4%
    688
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    274
    +0.11
    0.06
    688
    +0.10
    0.06
    70
    +0.09
    0.06
    Negative Logits
    estern
    -0.79
    ï¸
    -0.70
    folios
    -0.67
    =~=~
    -0.65
    ï¸ı
    -0.63
    ritional
    -0.63
    EDIT
    -0.63
    Pont
    -0.62
    wx
    -0.61
    pleting
    -0.60
    POSITIVE LOGITS
     goodbye
    1.38
     aloud
    0.96
     hello
    0.95
     bluntly
    0.85
     farewell
    0.83
     nothing
    0.82
     unequivocally
    0.78
     they
    0.77
     Goodbye
    0.76
     he
    0.75
    Activations Density 0.187%

    No Known Activations