© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 32664
    Prev
    Next
    INDEX
    Explanations

    references to specific locations and their corresponding contexts

    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
    534
    +0.12
    0.6%
    108
    +0.12
    0.6%
    165
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    476
    +0.12
    0.05
    168
    +0.12
    0.06
    757
    +0.10
    0.04
    Negative Logits
    since
    -0.66
    thanks
    -0.65
    emouth
    -0.65
    emort
    -0.62
    Recipe
    -0.62
     externalToEVAOnly
    -0.60
    due
    -0.60
    iak
    -0.59
    é¾įå¥ij士
    -0.59
     disadvant
    -0.58
    POSITIVE LOGITS
     lies
    1.43
     resides
    1.39
     sits
    1.35
     hangs
    1.31
     lur
    1.22
     lie
    1.15
     rests
    1.14
     stands
    1.11
     reside
    1.10
     emerges
    1.07
    Activations Density 1.238%

    No Known Activations