© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenAI · Sparse Autoencoder for GPT2-Small - v5 2024
    5. GPT2-Small
    7. Residual Post - 32k
    9. 10-RES_POST_32K-OAI
    11. 27705
    Prev
    Next
    INDEX
    Explanations

    references to liver health and its associated medical conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res_post_32k-oai
    Configuration
    jbloom/GPT2-Small-OAI-v5-32k-resid-post-SAEs/v5_32k_layer_10.pt
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    32,768
    Data Type
    torch.float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    standard
    Context Size
    64
    Dataset
    Skylion007/openwebtext
    Activation Function
    topk
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    414
    +0.11
    0.5%
    248
    +0.09
    0.4%
    732
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.11
    0.08
    594
    +0.09
    0.06
    516
    +0.09
    0.06
    Negative Logits
    cies
    -0.72
    pants
    -0.71
    behind
    -0.70
    glers
    -0.69
    quad
    -0.69
    dream
    -0.69
    psons
    -0.69
    urat
    -0.69
    eyes
    -0.68
    Deal
    -0.68
    POSITIVE LOGITS
     dysfunction
    0.84
     oxidative
    0.84
     covari
    0.84
     morphology
    0.82
     outcomes
    0.82
     composition
    0.81
     responsiveness
    0.79
     functional
    0.79
     heterogeneity
    0.79
    âĢIJ
    0.79
    Activations Density 0.659%

    No Known Activations