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 1536
    5. 8-RES_FS1536-JB
    6. 1450
    Prev
    Next
    INDEX
    Explanations

    words related to change, growth, and progress

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs1536-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_1536
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    1,536
    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
    123
    +0.10
    0.5%
    365
    +0.10
    0.5%
    555
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    608
    +0.10
    0.13
    712
    +0.10
    0.05
    234
    +0.10
    0.08
    Negative Logits
     helicop
    -0.69
    ILE
    -0.65
    raine
    -0.64
    Newsletter
    -0.64
     Vessel
    -0.63
    Train
    -0.63
     Uni
    -0.62
     Surve
    -0.61
    gov
    -0.61
    conservancy
    -0.61
    POSITIVE LOGITS
     origins
    1.20
     significance
    1.17
     resemblance
    1.10
     relevance
    1.08
     complexity
    1.03
     merits
    1.03
     implications
    1.03
     drawbacks
    1.01
     roots
    0.96
     flaws
    0.96
    Activations Density 3.426%

    No Known Activations