© 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. 20880
    Prev
    Next
    INDEX
    Explanations

    mentions of a specific word starting with "Sin"

    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
    195
    +0.11
    0.5%
    728
    +0.09
    0.4%
    459
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    728
    +0.11
    0.01
    386
    +0.09
    0.01
    161
    +0.09
    0.01
    Negative Logits
    è¦ļéĨĴ
    -0.78
    enance
    -0.74
    dropping
    -0.65
    berman
    -0.64
     principals
    -0.64
     deficits
    -0.63
    ĵĺ
    -0.62
    tops
    -0.62
    æ©Ł
    -0.62
    awei
    -0.61
    POSITIVE LOGITS
    atra
    1.15
    ned
    1.15
    clair
    1.12
    ews
    1.12
    ners
    1.11
    uous
    1.10
    estro
    1.04
    ister
    1.00
    ew
    0.97
    bad
    0.94
    Activations Density 0.021%

    No Known Activations