© 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. 37038
    Prev
    Next
    INDEX
    Explanations

    references to strategic locations, particularly in contexts related to military and geopolitical discussions

    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
    288
    +0.17
    0.8%
    549
    +0.13
    0.6%
    99
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.17
    0.01
    391
    +0.13
    0.01
    549
    +0.12
    0.01
    Negative Logits
    andro
    -0.80
    istry
    -0.78
    displayText
    -0.78
    nih
    -0.76
    spir
    -0.75
     Leilan
    -0.74
    respond
    -0.74
    uci
    -0.72
    hua
    -0.71
    flix
    -0.70
    POSITIVE LOGITS
     stronghold
    0.94
     strongh
    0.88
     Beir
    0.71
    holder
    0.70
     cities
    0.67
     elector
    0.67
     Shoals
    0.66
    hold
    0.65
     city
    0.64
     sites
    0.64
    Activations Density 0.009%

    No Known Activations