© 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 EvalsExportsAPI 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. 19732
    Prev
    Next
    INDEX
    Explanations

    information related to music albums, including details like release dates, chart positions, and critical reception

    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
    16
    +0.13
    0.6%
    256
    +0.10
    0.5%
    386
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    362
    +0.13
    0.05
    16
    +0.10
    0.04
    396
    +0.10
    0.03
    Negative Logits
     repaid
    -0.77
    artifacts
    -0.73
     lied
    -0.67
     innocence
    -0.66
     ens
    -0.66
     lapse
    -0.64
    ouf
    -0.64
    packs
    -0.63
    cised
    -0.63
     acquies
    -0.63
    POSITIVE LOGITS
     Billboard
    1.07
    ottest
    0.95
     Forbes
    0.87
     charts
    0.85
     Alexa
    0.85
     Dictionary
    0.81
     Cannes
    0.80
     trending
    0.80
     rankings
    0.79
     Yelp
    0.78
    Activations Density 0.223%

    No Known Activations