© 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. 775
    Prev
    Next
    INDEX
    Explanations

    statements of hope or encouragement

    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
    575
    +0.09
    0.4%
    679
    +0.09
    0.4%
    239
    +0.08
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    449
    +0.09
    0.03
    8
    +0.09
    0.03
    701
    +0.08
    0.03
    Negative Logits
    pes
    -0.76
    vation
    -0.66
    inas
    -0.66
    ItemImage
    -0.64
    eas
    -0.63
    cffffcc
    -0.63
    女
    -0.62
     Peninsula
    -0.61
    ces
    -0.60
    kw
    -0.60
    POSITIVE LOGITS
     someday
    1.10
     congr
    0.71
     whoever
    0.70
    reprene
    0.69
    lessly
    0.69
     somebody
    0.67
    fully
    0.67
    terday
    0.66
    ful
    0.65
     unborn
    0.64
    Activations Density 0.052%

    No Known Activations