© 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. 13690
    Prev
    Next
    INDEX
    Explanations

    organizations, groups, units, channels, models, routes, and behaviors mentioned in various contexts within longer texts

    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
    +0.23
    1.1%
    481
    +0.23
    1.1%
    447
    +0.21
    1.0%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    464
    +0.23
    0.06
    266
    +0.23
    0.04
    480
    +0.21
    0.01
    Negative Logits
    âĸ¬
    -0.65
    ãĥ¼ãĥĨ
    -0.63
     Azerb
    -0.63
     Niet
    -0.62
     Gaw
    -0.60
     Moroc
    -0.57
    ONSORED
    -0.54
    Thompson
    -0.53
     Palest
    -0.53
    Bey
    -0.53
    POSITIVE LOGITS
    ource
    1.14
    peed
    1.06
    pace
    1.06
    heet
    1.06
    mith
    1.03
    paces
    1.02
    ystem
    1.02
    hip
    1.02
    cript
    0.98
    afety
    0.97
    Activations Density 0.199%

    No Known Activations