© 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. 22928
    Prev
    Next
    INDEX
    Explanations

    references to roles and responsibilities in film and television industry processes, particularly involving direction and production

    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
    101
    +0.11
    0.5%
    555
    +0.10
    0.5%
    123
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    505
    +0.11
    0.03
    555
    +0.10
    0.03
    101
    +0.10
    0.04
    Negative Logits
    ym
    -0.67
    Usage
    -0.65
    uder
    -0.61
    Recomm
    -0.60
    Availability
    -0.59
    asta
    -0.59
     pretext
    -0.58
     grate
    -0.58
    iability
    -0.57
     degrade
    -0.57
    POSITIVE LOGITS
     overseeing
    0.77
     the
    0.67
    secret
    0.66
    orously
    0.65
     Countdown
    0.65
     them
    0.63
    ahime
    0.63
    cean
    0.63
     negotiations
    0.63
    İĭ
    0.62
    Activations Density 0.108%

    No Known Activations