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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Feature Splitting for GPT2-Small
    3. GPT2-Small
    4. Residual Feature Splitting 12288
    5. 8-RES_FS12288-JB
    6. 1011
    Prev
    Next
    INDEX
    Explanations

    phrases related to administrative regulations and protocols

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs12288-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_12288
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    12,288
    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
    756
    +0.13
    0.6%
    460
    +0.10
    0.5%
    570
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    756
    +0.13
    -0.02
    570
    +0.10
    0.02
    49
    +0.10
    0.07
    Negative Logits
    xit
    -0.74
     âĵĺ
    -0.70
    isode
    -0.63
    SPONSORED
    -0.60
     Together
    -0.60
    hens
    -0.57
     Beginning
    -0.57
    xon
    -0.56
    lez
    -0.56
    âĢİ
    -0.56
    POSITIVE LOGITS
     already
    0.83
     constantly
    0.71
     scarce
    0.69
     notoriously
    0.69
     finite
    0.69
     technically
    0.67
     pree
    0.66
     outnumbered
    0.66
     rarely
    0.66
    )</
    0.65
    Activations Density 1.328%

    No Known Activations