© 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. 41574
    Prev
    Next
    INDEX
    Explanations

    the name "Ali" in various contexts

    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
    459
    +0.13
    0.6%
    274
    +0.10
    0.5%
    502
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    299
    +0.13
    0.01
    757
    +0.10
    0.01
    659
    +0.10
    0.01
    Negative Logits
    acters
    -0.88
    olicy
    -0.84
    IAL
    -0.77
    ilaterally
    -0.76
    ly
    -0.75
    ividual
    -0.73
    nect
    -0.73
    sylvania
    -0.71
    osuke
    -0.70
    lished
    -0.68
    POSITIVE LOGITS
    yah
    1.28
    ño
    1.02
    ensis
    0.98
    Äĩ
    0.96
    ñ
    0.94
    ña
    0.86
    ère
    0.86
    ya
    0.83
    WAYS
    0.82
    ë
    0.82
    Activations Density 0.006%

    No Known Activations