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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & 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. 46121
    Prev
    Next
    INDEX
    Explanations

    references to financial institutions, specifically focusing on the term "Bundesbank."

    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
    679
    +0.17
    0.8%
    4
    +0.12
    0.5%
    578
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    537
    +0.17
    0.01
    578
    +0.12
    0.01
    288
    +0.10
    0.01
    Negative Logits
    ously
    -0.86
    osal
    -0.72
    mares
    -0.70
    OA
    -0.67
    lier
    -0.66
    istically
    -0.66
    ous
    -0.65
    ebook
    -0.64
    obar
    -0.64
     Doe
    -0.63
    POSITIVE LOGITS
    wana
    1.19
    layer
    1.00
    heet
    0.96
    hift
    0.89
    liga
    0.86
    pring
    0.85
    peed
    0.83
    afety
    0.83
    hirt
    0.82
    ettings
    0.81
    Activations Density 0.014%

    No Known Activations