© 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. 32018
    Prev
    Next
    INDEX
    Explanations

    terms related to biochemical interactions and cell signaling

    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
    71
    +0.11
    0.5%
    419
    +0.11
    0.5%
    284
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    314
    +0.11
    -0.00
    365
    +0.11
    0.01
    701
    +0.09
    0.03
    Negative Logits
     paranormal
    -0.59
    borg
    -0.59
    bourg
    -0.59
     commentary
    -0.58
    boxing
    -0.58
    ................................................................
    -0.57
     geo
    -0.56
    iety
    -0.56
    ################
    -0.56
    IUM
    -0.56
    POSITIVE LOGITS
    yl
    0.94
    rin
    0.84
    rase
    0.82
    amide
    0.77
    ylan
    0.77
    zin
    0.76
    ptives
    0.76
    raz
    0.74
    rub
    0.72
    ccoli
    0.69
    Activations Density 0.562%

    No Known Activations