© 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. 22260
    Prev
    Next
    INDEX
    Explanations

    instances of the word "re" and its variations in context

    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
    373
    +0.13
    0.6%
    555
    +0.10
    0.5%
    503
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    503
    +0.13
    0.01
    477
    +0.10
    0.01
    706
    +0.09
    0.01
    Negative Logits
     Teach
    -0.64
     Bord
    -0.64
    ilitarian
    -0.60
     Oy
    -0.58
     Galile
    -0.58
    knife
    -0.57
     RPGs
    -0.56
     Sparrow
    -0.56
    vironments
    -0.55
     Mellon
    -0.55
    POSITIVE LOGITS
    taboola
    1.01
    qus
    0.84
    interstitial
    0.79
    authorized
    0.76
    activate
    0.74
    register
    0.74
    Capt
    0.73
    valid
    0.72
    submit
    0.72
    lev
    0.70
    Activations Density 0.016%

    No Known Activations