© 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. 22435
    Prev
    Next
    INDEX
    Explanations

    phrases indicating the ability to opt-out or unsubscribe at any time

    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
    604
    +0.11
    0.5%
    420
    +0.09
    0.5%
    373
    +0.08
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    735
    +0.11
    0.01
    604
    +0.09
    0.01
    284
    +0.08
    0.01
    Negative Logits
    pher
    -0.77
    abal
    -0.71
    enhagen
    -0.67
    imer
    -0.63
    aceae
    -0.61
    orer
    -0.61
    ufact
    -0.60
    ãĥķãĤ¡
    -0.58
    isible
    -0.58
    entric
    -0.58
    POSITIVE LOGITS
    iggins
    0.66
     avatar
    0.65
     preferences
    0.63
     Privacy
    0.60
     withdraw
    0.59
     snipp
    0.59
     moral
    0.58
     login
    0.57
    ¶æ
    0.57
     withdrawal
    0.57
    Activations Density 0.020%

    No Known Activations