© 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. 8848
    Prev
    Next
    INDEX
    Explanations

    phrases related to competition and overcoming obstacles

    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
    526
    +0.12
    0.6%
    181
    +0.12
    0.5%
    540
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    636
    +0.12
    0.03
    526
    +0.12
    0.01
    181
    +0.12
    0.02
    Negative Logits
    fecture
    -0.77
    pora
    -0.76
    ffe
    -0.76
    ADD
    -0.73
    GREEN
    -0.69
     Authorization
    -0.66
    annels
    -0.65
    ndum
    -0.65
    iosis
    -0.65
    amia
    -0.65
    POSITIVE LOGITS
     crap
    1.09
     odds
    1.02
     hardest
    0.92
     senseless
    0.88
     drum
    0.86
     shit
    0.84
     toughest
    0.77
     drums
    0.75
     chops
    0.73
     bulls
    0.73
    Activations Density 0.084%

    No Known Activations