© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 23915
    Prev
    Next
    INDEX
    Explanations

    references to specific dates, events, or statistics

    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
    480
    +0.60
    8.1%
    373
    +0.19
    2.5%
    266
    +0.14
    1.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    480
    +0.60
    0.06
    266
    +0.19
    0.23
    373
    +0.14
    -0.14
    Negative Logits
    tein
    -0.21
    Sov
    -0.19
    eus
    -0.18
    £ı
    -0.17
    abouts
    -0.17
     ben
    -0.16
     sul
    -0.16
     wagon
    -0.16
    iens
    -0.16
    alore
    -0.16
    POSITIVE LOGITS
    Screenshot
    0.17
    )--
    0.15
    reenshots
    0.15
    ifies
    0.15
    atform
    0.15
    isSpecialOrderable
    0.14
    taboola
    0.14
    Cover
    0.14
     âĢº
    0.14
    github
    0.14
    Activations Density 7.097%

    No Known Activations