© 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. 26480
    Prev
    Next
    INDEX
    Explanations

    occurrences of the name "Ang"

    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
    549
    +0.20
    0.9%
    314
    +0.10
    0.5%
    8
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    549
    +0.20
    0.01
    659
    +0.10
    0.02
    701
    +0.09
    0.01
    Negative Logits
     wart
    -0.72
    ngth
    -0.67
    ãĥ¼ãĥ³
    -0.64
     compensated
    -0.64
    notice
    -0.63
     externalToEVAOnly
    -0.63
    dfx
    -0.59
    iquid
    -0.57
    OHN
    -0.57
     aperture
    -0.57
    POSITIVE LOGITS
    uish
    1.20
    rily
    1.18
    lia
    1.08
    sty
    1.07
    strom
    1.02
    ela
    0.94
    rier
    0.94
    ular
    0.94
    lers
    0.92
    lic
    0.91
    Activations Density 0.058%

    No Known Activations