© 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. 1261
    Prev
    Next
    INDEX
    Explanations

    mentions of personal experiences or stories in a narrative form

    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
    195
    +0.10
    0.5%
    236
    +0.10
    0.5%
    263
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    236
    +0.10
    0.06
    60
    +0.10
    0.05
    483
    +0.10
    0.04
    Negative Logits
    oubted
    -0.71
    topic
    -0.67
    ãģĮ
    -0.64
    izu
    -0.61
    ãģ¨
    -0.60
    oubt
    -0.59
    odder
    -0.58
     territory
    -0.57
    UM
    -0.57
    ãĥĩãĤ£
    -0.57
    POSITIVE LOGITS
    soever
    0.93
    ls
    0.84
    beit
    0.83
    lers
    0.78
    ling
    0.77
     much
    0.73
    ells
    0.71
    ars
    0.70
    itzer
    0.69
    lings
    0.68
    Activations Density 0.091%

    No Known Activations