© 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. 22538
    Prev
    Next
    INDEX
    Explanations

    scientific terms and jargon related to research methodologies and findings

    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
    586
    +0.14
    0.6%
    306
    +0.09
    0.4%
    317
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    586
    +0.14
    0.03
    306
    +0.09
    0.03
    317
    +0.09
    0.02
    Negative Logits
     Hardcore
    -0.84
     evict
    -0.82
    gamer
    -0.73
    estate
    -0.71
    venge
    -0.70
     booze
    -0.66
     Philly
    -0.66
     condos
    -0.65
     GTA
    -0.65
     whine
    -0.64
    POSITIVE LOGITS
    Study
    1.15
    doi
    1.12
     manuscript
    1.10
    Abstract
    1.06
    Acknowled
    1.06
    uscript
    1.05
    authors
    1.05
    doctoral
    1.01
     Supplementary
    0.99
     PubMed
    0.98
    Activations Density 0.174%

    No Known Activations