© 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. 6118
    Prev
    Next
    INDEX
    Explanations

    possessive forms followed by verbs or phrases indicating actions performed by a person

    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
    480
    +0.21
    1.0%
    447
    +0.17
    0.8%
    87
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    696
    +0.21
    0.01
    340
    +0.17
    0.01
    28
    +0.12
    0.01
    Negative Logits
     Niet
    -0.69
    å§
    -0.68
     horizont
    -0.67
    ãĥ¼ãĥĨ
    -0.65
     fert
    -0.65
     Chero
    -0.63
     Seym
    -0.62
     Swed
    -0.62
    âĨij
    -0.62
     Kurd
    -0.62
    POSITIVE LOGITS
    lash
    0.86
    utenberg
    0.79
    rael
    0.76
    ELF
    0.75
    rimp
    0.74
    reet
    0.73
    hi
    0.72
    weet
    0.72
    ead
    0.72
    ourge
    0.71
    Activations Density 0.028%

    No Known Activations