© 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. 32616
    Prev
    Next
    INDEX
    Explanations

    references to names and titles, often related to people or notable concepts

    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
    373
    +0.13
    0.6%
    407
    +0.11
    0.5%
    458
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    314
    +0.13
    -0.01
    659
    +0.11
    0.04
    232
    +0.11
    0.04
    Negative Logits
    BLE
    -0.83
    alog
    -0.76
    hedral
    -0.75
    onal
    -0.75
    vable
    -0.74
    bles
    -0.73
    aed
    -0.72
    oling
    -0.72
    aum
    -0.71
    ptin
    -0.70
    POSITIVE LOGITS
     Flags
    0.64
    is
    0.60
     guess
    0.59
    ãĥ³ãĤ¸
    0.55
     guesses
    0.55
     Job
    0.55
     Sir
    0.54
     Lords
    0.54
     assortment
    0.54
     Execution
    0.53
    Activations Density 0.287%

    No Known Activations