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. 7876
    Prev
    Next
    INDEX
    Explanations

    phrases related to deadlines or completion

    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
    373
    +0.12
    0.5%
    571
    +0.12
    0.5%
    218
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    571
    +0.12
    0.03
    319
    +0.12
    0.03
    547
    +0.11
    0.02
    Negative Logits
    uni
    -0.71
    itsch
    -0.64
    hemy
    -0.62
    RNA
    -0.61
     Parenthood
    -0.61
    rote
    -0.60
    avorite
    -0.60
     guiIcon
    -0.59
     ub
    -0.58
    hemat
    -0.56
    POSITIVE LOGITS
    owment
    1.32
    ocrine
    0.98
    angering
    0.94
    game
    0.89
    liest
    0.84
    cember
    0.83
     thereof
    0.79
    points
    0.78
    ear
    0.77
    ocrin
    0.75
    Activations Density 0.038%

    No Known Activations