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

    Neuronpedia

    Jacobian LensNEW
    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. 1483
    Prev
    Next
    INDEX
    Explanations

    phrases related to political actions and decisions

    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
    608
    +0.15
    0.7%
    310
    +0.12
    0.6%
    165
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    608
    +0.15
    0.06
    310
    +0.12
    0.04
    385
    +0.11
    0.04
    Negative Logits
    clud
    -0.78
    llo
    -0.69
     uploaded
    -0.67
    lla
    -0.65
    tracks
    -0.65
    igr
    -0.64
     largeDownload
    -0.63
    entimes
    -0.63
    ended
    -0.63
    alore
    -0.63
    POSITIVE LOGITS
     whoever
    0.89
     accommodate
    0.88
     appease
    0.86
     commemorate
    0.79
     whichever
    0.79
     avoid
    0.78
     compensate
    0.76
     someone
    0.75
     fend
    0.72
     outsiders
    0.71
    Activations Density 0.128%

    No Known Activations