Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Feature Splitting for GPT2-Small
    3. GPT2-Small
    4. Residual Feature Splitting 24576
    5. 8-RES_FS24576-JB
    6. 19265
    Prev
    Next
    INDEX
    Explanations

    information related to election results and political candidates

    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
    720
    +0.11
    0.5%
    452
    +0.09
    0.4%
    243
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    183
    +0.11
    0.04
    603
    +0.09
    0.03
    376
    +0.09
    0.03
    Negative Logits
    ĸļ
    -0.84
    IDER
    -0.77
    uras
    -0.67
    eco
    -0.66
     derivative
    -0.65
    Factor
    -0.63
     pros
    -0.63
    zie
    -0.63
    artifacts
    -0.62
     deprecated
    -0.61
    POSITIVE LOGITS
     reelection
    1.19
     majorities
    1.08
    election
    1.08
     votes
    1.03
     elections
    1.00
     electoral
    1.00
     landslide
    1.00
    elect
    1.00
     elector
    0.99
     election
    0.96
    Activations Density 0.162%

    No Known Activations