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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Feature Splitting for GPT2-Small
    5. GPT2-Small
    7. Residual Feature Splitting 49152
    9. 8-RES_FS49152-JB
    11. 37166
    Prev
    Next
    INDEX
    Explanations

    mentions of Donald Trump and related actions or discussions involving him

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs49152-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_49152
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    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
    684
    +0.11
    0.5%
    27
    +0.09
    0.4%
    604
    +0.08
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    184
    +0.11
    0.01
    682
    +0.09
    0.01
    684
    +0.08
    0.01
    Negative Logits
    gnu
    -0.68
    etheless
    -0.66
    ufact
    -0.64
    endum
    -0.59
     Magicka
    -0.59
     glim
    -0.58
    ifully
    -0.58
    viation
    -0.57
     fra
    -0.57
    Footnote
    -0.56
    POSITIVE LOGITS
     Kavanaugh
    0.70
     wiret
    0.68
     Rosenstein
    0.67
     ï
    0.67
     dossier
    0.63
    afort
    0.61
    umenthal
    0.61
     mistress
    0.60
    ensitive
    0.60
     Oval
    0.60
    Activations Density 0.006%

    No Known Activations