© 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. 9123
    Prev
    Next
    INDEX
    Explanations

    technical information or specifications related to products

    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
    71
    +0.10
    0.5%
    258
    +0.10
    0.5%
    645
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    16
    +0.10
    0.04
    206
    +0.10
    0.04
    106
    +0.10
    0.04
    Negative Logits
    orian
    -0.61
     constructive
    -0.61
    INAL
    -0.61
     chanting
    -0.58
     coordinates
    -0.56
     somet
    -0.55
     believing
    -0.55
     proverb
    -0.54
     Morph
    -0.54
     translating
    -0.54
    POSITIVE LOGITS
     surveyed
    1.12
     reviewed
    0.90
     tested
    0.83
     polled
    0.82
     available
    0.79
     examined
    0.77
     analyzed
    0.77
     nationwide
    0.77
    olk
    0.77
    mentioned
    0.76
    Activations Density 0.457%

    No Known Activations