© 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 24576
    9. 8-RES_FS24576-JB
    11. 18913
    Prev
    Next
    INDEX
    Explanations

    words related to software security and technology

    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
    608
    +0.13
    0.6%
    495
    +0.10
    0.5%
    589
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    608
    +0.13
    0.08
    718
    +0.10
    0.06
    508
    +0.09
    0.06
    Negative Logits
     Recorded
    -0.69
    unciation
    -0.66
     Warning
    -0.64
     rolled
    -0.63
    rolled
    -0.63
     bombed
    -0.61
     fired
    -0.61
     echoed
    -0.60
     Observer
    -0.60
     Walking
    -0.59
    POSITIVE LOGITS
     maximize
    1.54
     ensure
    1.45
     accommodate
    1.35
     minimize
    1.34
     avoid
    1.29
     optimize
    1.27
     facilitate
    1.26
     achieve
    1.25
     satisfy
    1.25
     conserve
    1.24
    Activations Density 0.209%

    No Known Activations