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. 26107
    Prev
    Next
    INDEX
    Explanations

    references to civil rights

    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
    288
    +0.15
    0.7%
    616
    +0.14
    0.6%
    314
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    616
    +0.15
    0.03
    302
    +0.14
    0.03
    152
    +0.12
    0.03
    Negative Logits
     Hungry
    -0.74
    edin
    -0.68
    è¦ļéĨĴ
    -0.68
    ï¸ı
    -0.67
    hov
    -0.67
    cca
    -0.66
    HM
    -0.66
    HK
    -0.66
     Finder
    -0.66
    asus
    -0.65
    POSITIVE LOGITS
    izational
    1.37
     liberties
    1.11
     disobedience
    1.06
     servants
    1.04
    isations
    1.01
     Liberties
    0.97
    izing
    0.96
     rights
    0.94
     servant
    0.89
    ization
    0.88
    Activations Density 0.012%

    No Known Activations