© 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 24576
    9. 8-RES_FS24576-JB
    11. 1265
    Prev
    Next
    INDEX
    Explanations

    instructions related to physical exercises or technical tasks

    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
    448
    +0.12
    0.5%
    194
    +0.11
    0.5%
    9
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    678
    +0.12
    0.06
    526
    +0.11
    0.00
    737
    +0.10
    0.04
    Negative Logits
    akings
    -0.80
    Rum
    -0.74
     Flavoring
    -0.73
     Diesel
    -0.68
     Reloaded
    -0.66
     Trouble
    -0.63
    ologne
    -0.63
    ivals
    -0.63
     rumors
    -0.63
     suspicions
    -0.62
    POSITIVE LOGITS
     perpendicular
    1.53
     angled
    1.33
     horizontal
    1.27
     downwards
    1.26
     perpend
    1.21
     horizontally
    1.20
     axis
    1.16
     diagonal
    1.16
     vertical
    1.15
     vertically
    1.15
    Activations Density 0.460%

    No Known Activations