© 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. OpenAI · Sparse Autoencoder for GPT2-Small - v5 2024
    5. GPT2-Small
    7. Residual Post - 32k
    9. 8-RES_POST_32K-OAI
    11. 6962
    Prev
    Next
    INDEX
    Explanations

    references to interleukins and their roles in immune responses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_post_32k-oai
    Configuration
    jbloom/GPT2-Small-OAI-v5-32k-resid-post-SAEs/v5_32k_layer_8.pt
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    32,768
    Data Type
    torch.float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    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
    314
    +0.13
    0.6%
    319
    +0.10
    0.5%
    168
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    759
    +0.13
    0.04
    439
    +0.10
    0.04
    293
    +0.10
    0.04
    Negative Logits
    lain
    -0.78
     ende
    -0.67
    ly
    -0.67
     awa
    -0.66
    pload
    -0.66
    perature
    -0.64
     Crunch
    -0.63
    llan
    -0.61
    rane
    -0.60
    illed
    -0.60
    POSITIVE LOGITS
    ibrary
    1.13
    ength
    0.95
    UTION
    0.94
    oaded
    0.88
    anguage
    0.84
    enium
    0.82
    ORED
    0.79
    owship
    0.78
    DER
    0.76
    ove
    0.76
    Activations Density 0.249%

    No Known Activations