© 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. 24429
    Prev
    Next
    INDEX
    Explanations

    terms related to illegal activities and renovations

    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
    591
    +0.12
    0.5%
    563
    +0.11
    0.5%
    352
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    503
    +0.12
    0.03
    763
    +0.11
    0.03
    288
    +0.11
    0.04
    Negative Logits
     annoyance
    -0.83
     spoilers
    -0.78
     inaction
    -0.76
     interest
    -0.75
     attachment
    -0.72
     captive
    -0.71
     frustration
    -0.71
     frustrations
    -0.70
     resemblance
    -0.69
     disappointment
    -0.69
    POSITIVE LOGITS
    icably
    1.09
    ating
    1.09
    icked
    1.08
    iced
    1.07
    rouse
    1.06
    ated
    1.06
    icating
    1.06
    ribe
    1.06
    ased
    1.05
    istered
    1.05
    Activations Density 0.130%

    No Known Activations