© 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. 4823
    Prev
    Next
    INDEX
    Explanations

    commands and configurations related to software development tools and processes

    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
    255
    +0.12
    0.5%
    553
    +0.11
    0.5%
    289
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    289
    +0.12
    0.02
    326
    +0.11
    0.04
    255
    +0.10
    0.04
    Negative Logits
    ndra
    -0.92
    neau
    -0.85
    odcast
    -0.84
    agonists
    -0.82
    arak
    -0.80
     Hutch
    -0.79
    involved
    -0.79
    alth
    -0.79
    deals
    -0.77
    reprene
    -0.76
    POSITIVE LOGITS
     UTF
    1.42
    UTF
    1.35
     encoded
    1.30
     encoding
    1.21
    utf
    1.21
     Unicode
    1.21
     integers
    1.18
     strings
    1.18
     bytes
    1.15
     byte
    1.15
    Activations Density 0.184%

    No Known Activations