© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Feature Splitting for GPT2-Small
    5. GPT2-Small
    7. Residual Feature Splitting 24576
    9. 8-RES_FS24576-JB
    11. 19609
    Prev
    Next
    INDEX
    Explanations

    phrases related to timing or current situations

    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
    481
    +0.14
    0.6%
    544
    +0.09
    0.4%
    614
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    544
    +0.14
    0.02
    599
    +0.09
    0.01
    72
    +0.09
    0.01
    Negative Logits
     Cosponsors
    -0.77
     Hits
    -0.71
    arnaev
    -0.62
    emale
    -0.62
    arlane
    -0.59
    nce
    -0.59
    krit
    -0.59
     Strikes
    -0.59
    apeake
    -0.59
    amn
    -0.58
    POSITIVE LOGITS
     anyway
    0.78
    adays
    0.76
    abouts
    0.75
     incarnation
    0.66
     indications
    0.65
     unspecified
    0.63
    endment
    0.62
     anyways
    0.60
    hift
    0.60
    ody
    0.60
    Activations Density 0.022%

    No Known Activations