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. 26346
    Prev
    Next
    INDEX
    Explanations

    terms related to immigration and the movement of people across borders

    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
    422
    +0.11
    0.5%
    481
    +0.10
    0.5%
    565
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.11
    0.04
    439
    +0.10
    0.03
    575
    +0.10
    0.04
    Negative Logits
     Dent
    -0.63
     quir
    -0.63
     nutshell
    -0.63
    Cola
    -0.61
     brow
    -0.61
     topical
    -0.61
    enegger
    -0.60
     cand
    -0.59
    efer
    -0.57
    zel
    -0.57
    POSITIVE LOGITS
     into
    1.06
     routes
    1.03
     INTO
    1.00
    into
    0.89
     Into
    0.88
     destinations
    0.87
     route
    0.85
    away
    0.83
    istics
    0.81
     flows
    0.81
    Activations Density 0.105%

    No Known Activations