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. 43149
    Prev
    Next
    INDEX
    Explanations

    terms related to campaign finance

    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
    268
    +0.14
    0.6%
    174
    +0.13
    0.6%
    111
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    247
    +0.14
    0.01
    288
    +0.13
    0.02
    224
    +0.10
    0.01
    Negative Logits
    Sensor
    -0.86
    å°Ĩ
    -0.86
    é¾įå
    -0.80
    å¸
    -0.76
    Balt
    -0.74
    è¯
    -0.73
     Seas
    -0.72
     Carbuncle
    -0.68
    Hug
    -0.68
    ipolar
    -0.68
    POSITIVE LOGITS
     ALEC
    0.78
     disclosure
    0.74
     donations
    0.73
    raising
    0.69
    rollers
    0.68
    roll
    0.67
    eering
    0.67
     PACs
    0.67
     pamph
    0.66
     filings
    0.66
    Activations Density 0.037%

    No Known Activations