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 49152
    5. 8-RES_FS49152-JB
    6. 41170
    Prev
    Next
    INDEX
    Explanations

    the name "Clinton" and its variations throughout the text

    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
    567
    +0.12
    0.5%
    706
    +0.11
    0.5%
    288
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    567
    +0.12
    0.04
    706
    +0.11
    0.03
    395
    +0.10
    0.03
    Negative Logits
    teenth
    -0.81
    GGGGGGGG
    -0.72
    raints
    -0.71
     Gareth
    -0.68
    CAST
    -0.67
    lass
    -0.66
    aic
    -0.66
    DIS
    -0.66
    PDATE
    -0.66
    eatures
    -0.66
    POSITIVE LOGITS
     Clinton
    0.99
    Clinton
    0.96
     Rodham
    0.90
    clinton
    0.88
     herself
    0.87
    mia
    0.87
     impeachment
    0.86
    INTON
    0.84
    ite
    0.83
    istas
    0.83
    Activations Density 0.023%

    No Known Activations