© 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. 8941
    Prev
    Next
    INDEX
    Explanations

    words related to challenging conventional wisdom or uncharted territories

    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
    62
    +0.10
    0.5%
    472
    +0.09
    0.4%
    336
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    284
    +0.10
    0.02
    232
    +0.09
    0.02
    48
    +0.09
    0.01
    Negative Logits
    gra
    -0.68
    lette
    -0.67
    tti
    -0.66
    ãĥ©ãĥ³
    -0.62
    elson
    -0.62
    sov
    -0.61
    erness
    -0.61
    conn
    -0.60
    terday
    -0.60
    ppo
    -0.59
    POSITIVE LOGITS
    ĸļ
    1.12
    ĥ
    1.10
    ģ
    1.05
    Ģ
    1.02
    arted
    0.91
    Ĵ
    0.90
    ĺ
    0.85
    ĸ
    0.85
    ĵ
    0.84
    anging
    0.83
    Activations Density 0.035%

    No Known Activations