© 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. 22999
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "Inter" or related variations

    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
    288
    +0.11
    0.5%
    537
    +0.10
    0.4%
    523
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    537
    +0.11
    0.02
    523
    +0.10
    0.02
    232
    +0.09
    0.02
    Negative Logits
     deaf
    -0.80
     deduction
    -0.68
    ggies
    -0.64
    aughs
    -0.64
     tremend
    -0.63
     scratch
    -0.63
    ongs
    -0.63
    ħĭ
    -0.62
     jobs
    -0.62
    dylib
    -0.62
    POSITIVE LOGITS
    ventions
    1.21
    mediate
    1.15
    continental
    1.10
    mitt
    1.07
    section
    1.07
    sectional
    1.06
    lude
    1.05
    pol
    1.04
    medi
    1.03
    rupted
    1.01
    Activations Density 0.013%

    No Known Activations