© 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. 7400
    Prev
    Next
    INDEX
    Explanations

    phrases related to technical terms in computer programming, specifically related to web development and browsers

    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
    745
    +0.11
    0.5%
    353
    +0.11
    0.5%
    398
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    398
    +0.11
    0.02
    353
    +0.11
    0.02
    111
    +0.10
    0.02
    Negative Logits
    »Ĵ
    -0.73
    Ĥ¬
    -0.72
    ubric
    -0.62
     contrace
    -0.62
    livious
    -0.61
    ©¶æ
    -0.61
    angular
    -0.59
    holm
    -0.58
    imedia
    -0.57
    atever
    -0.57
    POSITIVE LOGITS
     Duty
    1.12
     duty
    0.92
    duty
    0.92
     Cthulhu
    0.75
     arms
    0.69
    ãĥ¼ãĥ³
    0.68
    tnc
    0.68
    onement
    0.65
    arching
    0.64
    icide
    0.64
    Activations Density 0.061%

    No Known Activations