© 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. 28039
    Prev
    Next
    INDEX
    Explanations

    references to scientific measurements or observations related to cells, particularly in the context of medical or biological research

    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
    314
    +0.15
    0.7%
    373
    +0.11
    0.5%
    388
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    388
    +0.15
    0.07
    698
    +0.11
    0.06
    225
    +0.10
    0.06
    Negative Logits
     Merchants
    -0.64
    theless
    -0.63
     srfAttach
    -0.62
     Sul
    -0.62
     Forge
    -0.61
    grain
    -0.61
     borough
    -0.60
    wise
    -0.60
     Jagu
    -0.59
     rectangle
    -0.59
    POSITIVE LOGITS
    Ds
    0.95
    Ns
    0.94
    ector
    0.91
    OPS
    0.86
    esters
    0.84
    illon
    0.84
    ixel
    0.84
    nyder
    0.81
    assadors
    0.81
    amily
    0.81
    Activations Density 0.848%

    No Known Activations