© 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 12288
    9. 8-RES_FS12288-JB
    11. 1585
    Prev
    Next
    INDEX
    Explanations

    phrases related to political activities and involvement

    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
    766
    +0.11
    0.5%
    665
    +0.10
    0.5%
    184
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    665
    +0.11
    0.09
    184
    +0.10
    0.05
    761
    +0.10
    0.05
    Negative Logits
    etimes
    -0.70
     whim
    -0.67
     wont
    -0.63
     span
    -0.63
     breeze
    -0.63
    cember
    -0.62
     teased
    -0.62
     stumble
    -0.61
    ylon
    -0.61
     flung
    -0.60
    POSITIVE LOGITS
     ASAP
    1.00
     urgently
    0.84
    igate
    0.81
    ipt
    0.80
    dress
    0.79
    heed
    0.76
     their
    0.75
     THEIR
    0.73
    owship
    0.67
    umm
    0.65
    Activations Density 0.528%

    No Known Activations