© 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. 27169
    Prev
    Next
    INDEX
    Explanations

    references to academic journals or publications

    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
    +0.14
    0.6%
    744
    +0.09
    0.4%
    15
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    744
    +0.14
    0.02
    648
    +0.09
    0.02
    461
    +0.09
    0.01
    Negative Logits
     Mellon
    -0.65
    fitting
    -0.59
     ceilings
    -0.57
    athing
    -0.57
    pload
    -0.56
     hashing
    -0.56
    adiq
    -0.55
    fits
    -0.55
     copies
    -0.54
    creen
    -0.54
    POSITIVE LOGITS
    uel
    0.69
    ale
    0.68
     Communications
    0.66
    ista
    0.66
    itant
    0.66
     Abstract
    0.65
     Experimental
    0.65
    aum
    0.64
    oggle
    0.64
    alid
    0.63
    Activations Density 0.093%

    No Known Activations