© 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 EvalsExportsinterp-engineNEWAPI 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. 4435
    Prev
    Next
    INDEX
    Explanations

    phrases revolving around academic environments and student demographics

    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
    36
    +0.17
    0.8%
    393
    +0.12
    0.6%
    481
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    36
    +0.17
    0.07
    704
    +0.12
    0.03
    390
    +0.10
    0.03
    Negative Logits
    intent
    -0.99
    errors
    -0.84
    events
    -0.84
    iev
    -0.78
    cies
    -0.77
    ancies
    -0.76
    doms
    -0.76
    rants
    -0.75
    ichen
    -0.73
    chev
    -0.72
    POSITIVE LOGITS
     reminder
    1.12
     catalyst
    1.08
     precursor
    1.05
     deterrent
    1.04
     surrogate
    1.04
     conduit
    1.04
     standalone
    1.03
     gateway
    1.02
     complement
    1.01
     substitute
    1.01
    Activations Density 0.118%

    No Known Activations