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. 23141
    Prev
    Next
    INDEX
    Explanations

    commands and directives

    oai_token-act-pair · gpt-4o-miniTriggered 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
    718
    +0.13
    0.6%
    665
    +0.12
    0.5%
    373
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    665
    +0.13
    0.04
    718
    +0.12
    0.04
    508
    +0.11
    0.03
    Negative Logits
     Appears
    -0.77
    quickShipAvailable
    -0.70
    pires
    -0.65
     threaded
    -0.62
     impacting
    -0.61
     evid
    -0.60
     seams
    -0.60
     Results
    -0.59
    traumatic
    -0.59
     intrig
    -0.58
    POSITIVE LOGITS
     beware
    1.32
     evacuate
    1.19
     obey
    1.10
     behave
    1.05
     stop
    1.04
     refrain
    1.03
     avoid
    1.02
     comply
    1.00
     keep
    0.99
     ignore
    0.99
    Activations Density 0.089%

    No Known Activations