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. 26303
    Prev
    Next
    INDEX
    Explanations

    terms and phrases related to racial and environmental themes

    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
    97
    +0.15
    0.7%
    0
    +0.12
    0.6%
    55
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    0
    +0.15
    0.02
    97
    +0.12
    0.01
    155
    +0.12
    0.02
    Negative Logits
    ials
    -0.73
     Royals
    -0.70
    vation
    -0.70
     Thumbnails
    -0.67
     Presence
    -0.66
     Telesc
    -0.66
     Vessel
    -0.65
     Publication
    -0.64
    ger
    -0.64
     Passage
    -0.63
    POSITIVE LOGITS
     biased
    0.94
     charged
    0.88
     motivated
    0.86
     diverse
    0.86
     insensitive
    0.83
     divided
    0.80
     dispersed
    0.79
    culated
    0.79
     oriented
    0.79
     planted
    0.79
    Activations Density 0.008%

    No Known Activations