© 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
    3. Joseph Bloom · Feature Splitting for GPT2-Small
    5. GPT2-Small
    7. Residual Feature Splitting 12288
    9. 8-RES_FS12288-JB
    11. 10257
    Prev
    Next
    INDEX
    Explanations

    mentions of the concept of time, possibly related to a call for action or change

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs12288-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_12288
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    12,288
    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%
    184
    +0.11
    0.5%
    347
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    347
    +0.12
    0.03
    98
    +0.11
    0.03
    184
    +0.11
    0.02
    Negative Logits
    utsu
    -0.75
    ournal
    -0.74
    insula
    -0.73
    iership
    -0.73
    hemat
    -0.71
    riad
    -0.67
    obook
    -0.67
    agonist
    -0.67
    ourt
    -0.66
     perpend
    -0.65
    POSITIVE LOGITS
     anew
    0.77
     consuming
    0.74
    ful
    0.72
    llor
    0.71
     recons
    0.67
    ward
    0.65
     overdue
    0.63
    bringer
    0.62
    fully
    0.61
    consuming
    0.60
    Activations Density 0.056%

    No Known Activations