© 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. 6725
    Prev
    Next
    INDEX
    Explanations

    words related to medical research and interventions concerning arterial health and aging

    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
    374
    +0.14
    0.6%
    560
    +0.11
    0.5%
    373
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    373
    +0.14
    -0.01
    374
    +0.11
    0.02
    501
    +0.10
    0.02
    Negative Logits
    lihood
    -0.69
     MJ
    -0.66
     Mub
    -0.62
     skate
    -0.62
     Skydragon
    -0.59
    etheless
    -0.58
    ÄŁ
    -0.57
     Romans
    -0.56
     ankle
    -0.56
    unknown
    -0.56
    POSITIVE LOGITS
    aceous
    0.84
    rency
    0.82
    ç
    0.79
    udge
    0.68
    iform
    0.68
    icultural
    0.68
    idges
    0.68
    acle
    0.65
    iculture
    0.65
    locks
    0.65
    Activations Density 0.073%

    No Known Activations