Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & 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. 40076
    Prev
    Next
    INDEX
    Explanations

    currency symbols and financial values

    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
    314
    +0.15
    0.7%
    497
    +0.13
    0.6%
    120
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    182
    +0.15
    0.01
    518
    +0.13
    0.01
    124
    +0.12
    0.01
    Negative Logits
     Rib
    -0.76
     Dare
    -0.76
     Peb
    -0.73
     Pearce
    -0.70
     Twist
    -0.70
     Collider
    -0.69
     Citiz
    -0.69
     Gors
    -0.69
     Constantine
    -0.68
     Hasan
    -0.66
    POSITIVE LOGITS
    /$
    1.04
    -$
    0.97
    =~=~
    0.97
    /-
    0.94
    cffffcc
    0.88
    interstitial
    0.88
    £
    0.86
    6000
    0.84
    150
    0.84
    posts
    0.82
    Activations Density 0.004%

    No Known Activations