© 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. 13141
    Prev
    Next
    INDEX
    Explanations

    technical terms related to power systems, equipment, and processes, as well as numerical data

    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
    272
    +0.10
    0.5%
    26
    +0.10
    0.4%
    611
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    271
    +0.10
    0.02
    272
    +0.10
    0.02
    26
    +0.10
    0.02
    Negative Logits
    tein
    -0.89
    ledged
    -0.72
    {"
    -0.71
    lez
    -0.68
     Mortal
    -0.66
    lihood
    -0.66
     Donation
    -0.65
    utan
    -0.65
     Recogn
    -0.64
    Mobil
    -0.63
    POSITIVE LOGITS
    idge
    1.11
     temperatures
    0.93
     cooled
    0.92
     cooling
    0.90
    achine
    0.88
     climates
    0.84
    ocaust
    0.82
    Cool
    0.78
     cooker
    0.76
     tem
    0.74
    Activations Density 0.032%

    No Known Activations