© 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. 31934
    Prev
    Next
    INDEX
    Explanations

    references to stem cell research and related topics

    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
    387
    +0.13
    0.6%
    506
    +0.11
    0.5%
    312
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    482
    +0.13
    0.06
    232
    +0.11
    0.07
    128
    +0.10
    0.04
    Negative Logits
    Interstitial
    -0.92
    joice
    -0.69
    !/
    -0.65
     eh
    -0.64
     nowhere
    -0.62
     shoulders
    -0.61
     LOL
    -0.61
     veter
    -0.60
     AMERICA
    -0.59
    stay
    -0.59
    POSITIVE LOGITS
    ake
    1.02
    aters
    0.78
    abil
    0.74
    oking
    0.73
    asi
    0.73
    ifling
    0.70
    agn
    0.69
    rimination
    0.68
    igma
    0.67
    igham
    0.67
    Activations Density 0.545%

    No Known Activations