© 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 EvalsExportsinterp-engineNEWAPI 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. 14017
    Prev
    Next
    INDEX
    Explanations

    information related to technological devices or operations

    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
    616
    +0.11
    0.5%
    314
    +0.10
    0.5%
    395
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    639
    +0.11
    0.03
    537
    +0.10
    0.03
    610
    +0.10
    0.02
    Negative Logits
     pulp
    -0.60
     Cruiser
    -0.60
     Defendants
    -0.59
     gloom
    -0.58
     inflated
    -0.58
     disturbance
    -0.57
     HIP
    -0.56
     Jacket
    -0.56
     Fisheries
    -0.56
     snail
    -0.56
    POSITIVE LOGITS
    everal
    1.24
    ettings
    1.11
    peed
    1.09
    sembly
    1.07
    hift
    1.05
    uper
    0.99
    hell
    0.99
    chool
    0.99
    hare
    0.97
    mart
    0.96
    Activations Density 0.053%

    No Known Activations