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. 940
    Prev
    Next
    INDEX
    Explanations

    percentage values

    oai_token-act-pair · gpt-3.5-turboTriggered 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
    288
    +0.10
    0.4%
    745
    +0.09
    0.4%
    762
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    742
    +0.10
    0.02
    745
    +0.09
    0.01
    743
    +0.09
    0.02
    Negative Logits
    kefeller
    -0.80
     Dull
    -0.74
    ALLY
    -0.73
    PORT
    -0.73
    Attributes
    -0.73
    GROUP
    -0.70
    ITED
    -0.70
     Rav
    -0.69
    Merit
    -0.69
    EStream
    -0.69
    POSITIVE LOGITS
    imet
    1.38
    imeter
    1.07
     occupancy
    0.71
     humidity
    0.70
    aur
    0.70
     analyse
    0.69
    oning
    0.68
    bench
    0.67
    +.
    0.67
    osite
    0.66
    Activations Density 0.024%

    No Known Activations