© 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. 26394
    Prev
    Next
    INDEX
    Explanations

    components related to mathematical expressions and functions

    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
    3
    +0.13
    0.6%
    314
    +0.12
    0.5%
    425
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    352
    +0.13
    0.07
    158
    +0.12
    0.06
    621
    +0.10
    0.05
    Negative Logits
     certific
    -0.63
     ancest
    -0.61
     pave
    -0.60
     calibr
    -0.60
     asses
    -0.60
     coordination
    -0.59
     corrections
    -0.59
     impunity
    -0.58
     discretion
    -0.58
     acron
    -0.56
    POSITIVE LOGITS
     =>
    1.06
    ():
    0.98
     :
    0.92
    ":
    0.86
    >>\
    0.85
    ':
    0.84
    ":[
    0.83
    :(
    0.83
    ŀ
    0.82
    ¼
    0.82
    Activations Density 0.391%

    No Known Activations