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. 662
    Prev
    Next
    INDEX
    Explanations

    terms related to racial issues, particularly focusing on the Black community

    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
    57
    +0.11
    0.5%
    152
    +0.10
    0.4%
    447
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    57
    +0.11
    0.04
    96
    +0.10
    0.04
    152
    +0.10
    0.04
    Negative Logits
    ysis
    -0.87
    arium
    -0.78
    aghetti
    -0.75
     Canaver
    -0.70
    pload
    -0.70
    ascript
    -0.70
    uden
    -0.70
    ortmund
    -0.69
    iral
    -0.69
    OOL
    -0.69
    POSITIVE LOGITS
     supremacist
    1.15
     supremacists
    1.11
     youths
    1.06
     nationalist
    1.04
     youth
    0.94
     populations
    0.94
     nationalists
    0.93
     Lives
    0.93
     males
    0.92
     immigrants
    0.91
    Activations Density 0.099%

    No Known Activations