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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Feature Splitting for GPT2-Small
    5. GPT2-Small
    7. Residual Feature Splitting 768
    9. 8-RES_FS768-JB
    11. 674
    Prev
    Next
    INDEX
    Explanations

    words related to medical conditions and treatments

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs768-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_768
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    768
    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
    200
    +0.10
    0.5%
    658
    +0.09
    0.4%
    109
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    570
    +0.10
    0.01
    77
    +0.09
    0.08
    408
    +0.09
    0.15
    Negative Logits
    iron
    -0.86
    MIT
    -0.74
    jam
    -0.72
    Fear
    -0.72
    Jonathan
    -0.69
    odore
    -0.69
    Hunt
    -0.68
    ldon
    -0.67
    Eric
    -0.66
    Alert
    -0.66
    POSITIVE LOGITS
     genders
    1.33
     sizes
    1.32
     differing
    1.30
     shapes
    1.28
     configurations
    1.26
     varying
    1.26
     styles
    1.25
     colours
    1.22
     severity
    1.22
     different
    1.21
    Activations Density 6.341%

    No Known Activations