© 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. 16841
    Prev
    Next
    INDEX
    Explanations

    specific words related to a dataset-sanitization library and C++ programming syntax

    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
    480
    +0.06
    0.6%
    481
    +0.05
    0.5%
    459
    +0.05
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    620
    +0.06
    -0.01
    283
    +0.05
    -0.02
    711
    +0.05
    -0.01
    Negative Logits
    ilial
    -0.32
     UNCLASSIFIED
    -0.28
    én
    -0.27
    aclysm
    -0.26
    ulner
    -0.26
    otom
    -0.25
    apego
    -0.25
    rowth
    -0.25
    ellectual
    -0.25
    istor
    -0.24
    POSITIVE LOGITS
    RY
    0.26
    inos
    0.26
     Slim
    0.25
     Finder
    0.25
    ieu
    0.24
     thumbs
    0.24
    Skip
    0.24
    riott
    0.23
    EY
    0.23
     beware
    0.23
    Activations Density 2.969%

    No Known Activations