© 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. 18360
    Prev
    Next
    INDEX
    Explanations

    proper nouns and abbreviations of political figures or entities

    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
    +0.50
    2.7%
    87
    +0.17
    0.9%
    266
    +0.15
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    727
    +0.50
    0.05
    696
    +0.17
    0.06
    193
    +0.15
    0.05
    Negative Logits
     Seym
    -0.61
     compar
    -0.60
    eering
    -0.57
     curric
    -0.56
     Niet
    -0.56
     Nichols
    -0.53
     Moroc
    -0.52
     logistical
    -0.51
    ãĥ¼ãĥĨ
    -0.50
     increments
    -0.50
    POSITIVE LOGITS
    rael
    0.72
    ELF
    0.69
    ̶
    0.67
    reetings
    0.67
    leeve
    0.67
    utter
    0.65
    iple
    0.64
    ould
    0.63
    une
    0.63
    ears
    0.63
    Activations Density 0.192%

    No Known Activations