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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 8236
    Prev
    Next
    INDEX
    Explanations

    Proper names related to significant events, organizations, or individuals

    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
    163
    +0.12
    0.6%
    678
    +0.11
    0.5%
    466
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    232
    +0.12
    0.01
    466
    +0.11
    0.01
    659
    +0.10
    0.01
    Negative Logits
    luaj
    -0.71
    DragonMagazine
    -0.67
    e
    -0.64
     Hots
    -0.64
     reversible
    -0.62
     Homo
    -0.61
    figure
    -0.61
    ãĥ¼ãĥĨãĤ£
    -0.61
     redu
    -0.60
     Euras
    -0.60
    POSITIVE LOGITS
    lich
    1.24
    agan
    0.96
    acht
    0.92
    lein
    0.90
    ackers
    0.86
    kamp
    0.86
    mann
    0.85
    utable
    0.84
    acket
    0.82
    acking
    0.80
    Activations Density 0.010%

    No Known Activations