© 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 24576
    9. 8-RES_FS24576-JB
    11. 18714
    Prev
    Next
    INDEX
    Explanations

    references to political actions and beliefs

    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
    480
    +0.48
    2.4%
    266
    +0.10
    0.5%
    641
    +0.09
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    480
    +0.48
    0.01
    665
    +0.10
    0.08
    266
    +0.09
    0.08
    Negative Logits
    \-
    -0.59
     infamous
    -0.58
     unsuccessfully
    -0.56
    secret
    -0.56
     nicknamed
    -0.55
    Downloadha
    -0.54
    irin
    -0.53
    unknown
    -0.52
    amon
    -0.52
    cheon
    -0.52
    POSITIVE LOGITS
     ASAP
    0.85
     transparency
    0.83
     accountability
    0.83
     accountable
    0.79
     unbiased
    0.79
     sooner
    0.79
    respect
    0.79
     honest
    0.78
    cknow
    0.78
     decency
    0.77
    Activations Density 0.963%

    No Known Activations