© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 8150
    Prev
    Next
    INDEX
    Explanations

    proper names and titles related to sports

    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
    547
    +0.11
    0.5%
    420
    +0.11
    0.5%
    313
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    406
    +0.11
    0.01
    379
    +0.11
    0.01
    326
    +0.10
    0.01
    Negative Logits
    ion
    -0.73
    ually
    -0.67
    ional
    -0.65
    ION
    -0.64
    imation
    -0.63
     Pavilion
    -0.63
    imated
    -0.60
    WIND
    -0.60
    nah
    -0.60
    ionic
    -0.59
    POSITIVE LOGITS
    llan
    1.13
    astern
    0.86
    lli
    0.83
    llo
    0.83
    tails
    0.82
    ãĥ©ãĥ³
    0.81
    tta
    0.81
    zzi
    0.79
    tsky
    0.78
    ño
    0.76
    Activations Density 0.026%

    No Known Activations