© 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. 7541
    Prev
    Next
    INDEX
    Explanations

    phrases related to political issues and government actions

    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
    481
    +0.13
    0.6%
    567
    +0.10
    0.4%
    497
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    102
    +0.13
    0.06
    566
    +0.10
    0.04
    55
    +0.10
    0.05
    Negative Logits
    mentioned
    -0.72
    ukong
    -0.67
    Laughs
    -0.67
    yeah
    -0.66
     ['
    -0.65
    said
    -0.65
     mentions
    -0.65
     Yeah
    -0.64
    ozo
    -0.63
    Yeah
    -0.63
    POSITIVE LOGITS
     unfairly
    1.45
     unfair
    0.98
     outwe
    0.89
     misunderstood
    0.88
     unlawfully
    0.88
     underestimated
    0.87
     overest
    0.85
     disproportionately
    0.84
     underest
    0.83
     siph
    0.83
    Activations Density 0.416%

    No Known Activations