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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 12899
    Prev
    Next
    INDEX
    Explanations

    experiences, interactions, and activities happening in various locations or events

    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
    481
    +0.14
    0.6%
    426
    +0.10
    0.5%
    601
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    641
    +0.14
    0.05
    750
    +0.10
    0.03
    97
    +0.10
    0.03
    Negative Logits
     blaming
    -0.82
     estimating
    -0.77
    ItemImage
    -0.72
     refusing
    -0.72
    ItemTracker
    -0.70
     indicating
    -0.69
     tendency
    -0.69
     predicting
    -0.69
     calculates
    -0.68
     assumption
    -0.68
    POSITIVE LOGITS
     firsthand
    1.38
     scenery
    0.86
    agine
    0.83
     greatness
    0.82
     yourself
    0.79
     demos
    0.76
     whats
    0.76
     attractions
    0.76
     majesty
    0.75
    ocamp
    0.73
    Activations Density 0.280%

    No Known Activations