© 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 49152
    9. 8-RES_FS49152-JB
    11. 24031
    Prev
    Next
    INDEX
    Explanations

    references to time periods, specifically weeks and months

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs49152-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_49152
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    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
    760
    +0.13
    0.6%
    430
    +0.11
    0.5%
    688
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    760
    +0.13
    0.03
    430
    +0.11
    0.03
    651
    +0.09
    0.03
    Negative Logits
    omething
    -0.85
    urations
    -0.67
    emort
    -0.62
    ById
    -0.61
    76561
    -0.60
    ventus
    -0.59
    vae
    -0.59
    erate
    -0.58
    yre
    -0.58
     territ
    -0.57
    POSITIVE LOGITS
    days
    0.86
    night
    0.81
     episode
    0.77
    bush
    0.74
    DAY
    0.73
     edition
    0.71
     EDITION
    0.69
    isphere
    0.68
     installment
    0.66
    ç«
    0.66
    Activations Density 0.051%

    No Known Activations