© 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. 12229
    Prev
    Next
    INDEX
    Explanations

    medical and health-related terms and concepts

    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
    679
    +0.16
    0.7%
    447
    +0.12
    0.6%
    537
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    679
    +0.16
    0.07
    224
    +0.12
    0.07
    537
    +0.10
    0.07
    Negative Logits
    izoph
    -0.74
    bush
    -0.72
    aceous
    -0.69
    Reloaded
    -0.69
    ward
    -0.67
    bolt
    -0.67
    OUS
    -0.65
    FUL
    -0.63
    brew
    -0.61
    peat
    -0.61
    POSITIVE LOGITS
     alike
    1.01
    hips
    0.94
    hops
    0.85
     everywhere
    0.85
    hip
    0.84
    ateurs
    0.82
    paces
    0.82
     rejoice
    0.79
    afety
    0.79
     specializing
    0.78
    Activations Density 0.270%

    No Known Activations