© 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. 45765
    Prev
    Next
    INDEX
    Explanations

    mentions of the name "Jas" 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
    659
    +0.13
    0.6%
    504
    +0.10
    0.5%
    743
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    659
    +0.13
    0.01
    504
    +0.10
    0.01
    743
    +0.10
    0.01
    Negative Logits
     contiguous
    -0.76
     reconc
    -0.75
     census
    -0.67
    Ĥª
    -0.67
    ancial
    -0.65
     paycheck
    -0.64
     saline
    -0.64
     cavity
    -0.63
     Canterbury
    -0.62
     dues
    -0.61
    POSITIVE LOGITS
    mine
    1.40
    nah
    1.10
    quez
    0.96
    nan
    0.94
    seys
    0.93
    imoto
    0.91
    perse
    0.90
    coe
    0.88
    het
    0.88
    mol
    0.87
    Activations Density 0.006%

    No Known Activations