© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Feature Splitting for GPT2-Small
    5. GPT2-Small
    7. Residual Feature Splitting 12288
    9. 8-RES_FS12288-JB
    11. 10313
    Prev
    Next
    INDEX
    Explanations

    punctuation marks

    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
    314
    +0.15
    0.7%
    430
    +0.13
    0.6%
    45
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    6
    +0.15
    0.03
    751
    +0.13
    0.03
    430
    +0.10
    0.03
    Negative Logits
     millenn
    -0.75
     nodd
    -0.69
    rers
    -0.68
     adjunct
    -0.67
     booking
    -0.67
     qualitative
    -0.66
     welcome
    -0.64
     immersion
    -0.64
     creeping
    -0.63
     misunderstood
    -0.63
    POSITIVE LOGITS
    _.
    1.11
    NET
    1.10
    -.
    1.08
    gif
    1.07
    hack
    1.01
    Pa
    1.01
    wav
    0.98
    pdf
    0.95
    aspx
    0.93
    mobi
    0.93
    Activations Density 0.047%

    No Known Activations