© 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. 26392
    Prev
    Next
    INDEX
    Explanations

    references to keys

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Neuron Alignment
    Index
    Value
    % of L₁
    420
    +0.13
    0.6%
    314
    +0.11
    0.5%
    189
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    189
    +0.13
    0.02
    592
    +0.11
    0.02
    435
    +0.10
    0.02
    Negative Logits
    ALLY
    -0.66
    ICAN
    -0.64
     Colleges
    -0.64
     Fif
    -0.62
    ews
    -0.59
    ormal
    -0.59
     Interstellar
    -0.58
    ¬¼
    -0.57
    asca
    -0.57
    ylon
    -0.56
    POSITIVE LOGITS
    stroke
    1.55
    chain
    1.34
    */(
    1.29
    bind
    1.28
    pad
    1.27
    caps
    1.24
    stone
    1.22
    hole
    1.22
    binding
    1.20
    stro
    1.20
    Activations Density 0.135%

    No Known Activations