© 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. 7576
    Prev
    Next
    INDEX
    Explanations

    paragraphs expressing personal reflections and emotional intensity

    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
    408
    +0.11
    0.5%
    13
    +0.11
    0.5%
    554
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    13
    +0.11
    0.04
    554
    +0.11
    0.01
    369
    +0.10
    0.03
    Negative Logits
    days
    -0.71
     Digest
    -0.71
    etheless
    -0.69
    lus
    -0.63
    eming
    -0.62
     Provides
    -0.58
     Coverage
    -0.56
     Received
    -0.55
    ept
    -0.54
    arel
    -0.54
    POSITIVE LOGITS
     aside
    1.02
     emphasis
    0.85
     pedal
    0.83
     brakes
    0.83
     jeopardy
    0.83
     together
    0.81
     lid
    0.81
     toget
    0.80
     spotlight
    0.78
    rescent
    0.76
    Activations Density 0.125%

    No Known Activations