Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Feature Splitting for GPT2-Small
    3. GPT2-Small
    4. Residual Feature Splitting 24576
    5. 8-RES_FS24576-JB
    6. 1069
    Prev
    Next
    INDEX
    Explanations

    technical terms related to computer software and hardware support

    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
    447
    +0.13
    0.6%
    326
    +0.12
    0.5%
    590
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    575
    +0.13
    0.02
    288
    +0.12
    0.02
    326
    +0.10
    0.01
    Negative Logits
    eln
    -0.88
    orb
    -0.85
    fax
    -0.75
    orie
    -0.73
    romeda
    -0.71
    oral
    -0.71
    illion
    -0.70
    emi
    -0.69
    uras
    -0.69
    eur
    -0.68
    POSITIVE LOGITS
    tenance
    0.97
     starter
    0.84
    FIELD
    0.73
     kit
    0.72
     pitcher
    0.71
    starter
    0.70
    belt
    0.69
     beware
    0.68
    vier
    0.67
     kits
    0.67
    Activations Density 0.043%

    No Known Activations