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. 23842
    Prev
    Next
    INDEX
    Explanations

    phrases and terms related to governmental roles and functions

    oai_token-act-pair · gpt-4o-miniTriggered 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
    373
    +0.13
    0.6%
    669
    +0.11
    0.5%
    81
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    572
    +0.13
    0.03
    204
    +0.11
    0.03
    669
    +0.10
    0.03
    Negative Logits
     collaborators
    -0.66
     pedest
    -0.66
     tumble
    -0.65
    phrine
    -0.65
     therapists
    -0.64
     slic
    -0.63
    acci
    -0.61
     palms
    -0.60
    ritis
    -0.60
     mosquit
    -0.60
    POSITIVE LOGITS
     Legislative
    0.82
     Communications
    0.82
     Outs
    0.79
     Rings
    0.77
     Agriculture
    0.76
     Revenue
    0.75
    iture
    0.74
     Flags
    0.73
    Export
    0.73
     Export
    0.73
    Activations Density 0.066%

    No Known Activations