© 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 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. 7708
    Prev
    Next
    INDEX
    Explanations

    technical information related to mechanical parts and repairs

    oai_token-act-pair · gpt-3.5-turboTriggered 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
    756
    +0.13
    0.6%
    368
    +0.11
    0.5%
    219
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    756
    +0.13
    -0.02
    608
    +0.11
    0.06
    614
    +0.10
    0.03
    Negative Logits
    thood
    -0.77
    leans
    -0.69
    hid
    -0.66
    yt
    -0.65
    ãĤĭ
    -0.64
     herself
    -0.63
    ohan
    -0.62
    Untitled
    -0.62
    inosaur
    -0.62
     fame
    -0.62
    POSITIVE LOGITS
     abound
    0.83
     meanwhile
    0.74
     scarce
    0.58
     these
    0.58
     Freeman
    0.57
    ouses
    0.57
     periphery
    0.56
     Provincial
    0.56
     both
    0.55
     frantic
    0.55
    Activations Density 0.730%

    No Known Activations