© 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 49152
    9. 8-RES_FS49152-JB
    11. 45578
    Prev
    Next
    INDEX
    Explanations

    mentions of political parties

    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
    339
    +0.14
    0.6%
    288
    +0.13
    0.6%
    247
    +0.13
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    247
    +0.14
    0.03
    197
    +0.13
    0.03
    339
    +0.13
    0.03
    Negative Logits
     Grizz
    -0.81
     Kard
    -0.70
     Wheat
    -0.70
     Dull
    -0.70
     Drake
    -0.70
     Deter
    -0.70
     Hoo
    -0.69
    alam
    -0.67
    angelo
    -0.66
    ravings
    -0.65
    POSITIVE LOGITS
     affiliation
    1.06
    leader
    1.01
     leaders
    0.97
     leader
    0.97
     leadership
    0.97
     affili
    0.95
    Leader
    0.93
    leaders
    0.92
    members
    0.92
    arians
    0.92
    Activations Density 0.024%

    No Known Activations