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. 1137
    Prev
    Next
    INDEX
    Explanations

    adjectives describing a variety or range of things

    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
    99
    +0.11
    0.5%
    377
    +0.10
    0.5%
    153
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    99
    +0.11
    0.02
    153
    +0.10
    0.02
    372
    +0.10
    0.02
    Negative Logits
    nces
    -0.74
    illard
    -0.71
    nos
    -0.66
    ICAN
    -0.66
     Uriel
    -0.65
    adobe
    -0.64
    MENT
    -0.64
    ilan
    -0.64
    CB
    -0.62
    ador
    -0.61
    POSITIVE LOGITS
     swath
    1.02
    creen
    1.00
    open
    0.98
     scope
    0.96
    sword
    0.92
    sheets
    0.91
    spread
    0.91
     open
    0.91
    sheet
    0.89
     spectrum
    0.89
    Activations Density 0.025%

    No Known Activations