© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 14867
    Prev
    Next
    INDEX
    Explanations

    technical descriptions and specifications related to electronic devices

    oai_token-act-pair · gpt-3.5-turbo
    Triggered 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
    Neuron Alignment
    Index
    Value
    % of L₁
    640
    +0.14
    0.7%
    615
    +0.12
    0.6%
    680
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    680
    +0.14
    0.04
    615
    +0.12
    0.04
    577
    +0.11
    0.04
    Negative Logits
     advis
    -0.72
     entitlement
    -0.61
     trouble
    -0.59
     fung
    -0.59
     sustainability
    -0.58
     tentative
    -0.58
     offending
    -0.58
     worsh
    -0.58
     aside
    -0.58
     federation
    -0.58
    POSITIVE LOGITS
    0
    1.24
    5
    1.22
    00
    1.16
    jpg
    1.14
    25
    1.13
    75
    1.10
    06
    1.06
    6
    1.04
    02
    1.03
    000000
    1.03
    Activations Density 0.077%

    No Known Activations