© 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 49152
    9. 8-RES_FS49152-JB
    11. 45817
    Prev
    Next
    INDEX
    Explanations

    references to specific characters or individuals in a narrative or context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs49152-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_49152
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    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
    585
    +0.12
    0.6%
    526
    +0.11
    0.5%
    504
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    504
    +0.12
    0.01
    659
    +0.11
    0.01
    585
    +0.10
    0.01
    Negative Logits
    holders
    -0.83
     cavity
    -0.69
    spring
    -0.67
    è¦ļéĨĴ
    -0.67
     holders
    -0.67
     liner
    -0.66
    PLIED
    -0.63
     clutch
    -0.62
     skate
    -0.61
     carriers
    -0.61
    POSITIVE LOGITS
    iah
    1.28
    lyn
    1.11
    sey
    1.07
    uke
    1.07
    iane
    1.03
    ync
    0.99
    quez
    0.99
    hiba
    0.98
    seys
    0.98
    kens
    0.92
    Activations Density 0.002%

    No Known Activations