© 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 1536
    9. 8-RES_FS1536-JB
    11. 1155
    Prev
    Next
    INDEX
    Explanations

    phrases related to perspectives or viewpoints

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs1536-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_1536
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    1,536
    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
    393
    +0.13
    0.6%
    4
    +0.10
    0.5%
    170
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    53
    +0.13
    0.11
    362
    +0.10
    0.10
    393
    +0.10
    0.11
    Negative Logits
    Enlarge
    -0.73
    fml
    -0.68
     reperto
    -0.65
    ername
    -0.64
    amount
    -0.63
    ................................................................
    -0.62
     externalToEVAOnly
    -0.61
    azines
    -0.60
     Extras
    -0.59
    ME
    -0.58
    POSITIVE LOGITS
     contention
    0.88
     sorts
    0.87
     persuasion
    0.86
     theirs
    0.85
     origin
    0.84
     reckoning
    0.84
     yours
    0.83
     conscience
    0.83
     Excellence
    0.82
     ours
    0.81
    Activations Density 1.389%

    No Known Activations