© 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. 24380
    Prev
    Next
    INDEX
    Explanations

    terms related to surveillance, legal issues, and societal systems

    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
    481
    +0.22
    1.0%
    447
    +0.18
    0.9%
    712
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    225
    +0.22
    0.09
    288
    +0.18
    0.09
    575
    +0.11
    0.08
    Negative Logits
    itional
    -0.64
    姫
    -0.59
    etime
    -0.58
    empty
    -0.58
     retracted
    -0.55
     pronouns
    -0.54
    hair
    -0.54
    uld
    -0.54
    alle
    -0.53
     papers
    -0.52
    POSITIVE LOGITS
     spanning
    0.82
     consisting
    0.75
     involving
    0.74
     coupled
    0.74
     featuring
    0.74
     akin
    0.73
     amidst
    0.72
     centered
    0.71
     comprising
    0.71
     overseen
    0.69
    Activations Density 0.470%

    No Known Activations