© 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. 8684
    Prev
    Next
    INDEX
    Explanations

    terms related to biomedical research, specifically in the field of brain and blood-barrier structure and function, CNS pathologies, and protein involvement

    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
    373
    +0.11
    0.5%
    447
    +0.11
    0.5%
    7
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    7
    +0.11
    0.04
    38
    +0.11
    0.04
    157
    +0.10
    0.05
    Negative Logits
     Restaur
    -0.86
    Exit
    -0.80
     Bravo
    -0.78
    ibur
    -0.76
    ibles
    -0.75
    estate
    -0.73
     Loyal
    -0.73
    Residents
    -0.71
    iquette
    -0.70
    ihad
    -0.70
    POSITIVE LOGITS
     studies
    1.27
     hypothes
    1.19
     theorists
    1.17
     theories
    1.16
     scientific
    1.14
     philosophers
    1.14
     researchers
    1.13
     theor
    1.12
     scientists
    1.09
     scholarly
    1.08
    Activations Density 0.475%

    No Known Activations