© 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. 6627
    Prev
    Next
    INDEX
    Explanations

    phrases related to advancements in medical technology

    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
    37
    +0.12
    0.5%
    140
    +0.09
    0.4%
    370
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    37
    +0.12
    0.03
    48
    +0.09
    0.02
    6
    +0.09
    0.02
    Negative Logits
    ãĥī
    -0.89
    ãĥŃ
    -0.71
     transform
    -0.69
     domest
    -0.68
    uble
    -0.64
    romancer
    -0.63
     tropical
    -0.62
     wraps
    -0.62
    gran
    -0.61
     wrapping
    -0.61
    POSITIVE LOGITS
    I
    1.23
     I
    1.12
     II
    1.08
    II
    1.04
    Ire
    0.95
     IX
    0.88
    III
    0.87
     Ike
    0.83
     LI
    0.82
     Ich
    0.81
    Activations Density 0.091%

    No Known Activations