© 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. 8-RES_POST_32K-OAI
    11. 8982
    Prev
    Next
    INDEX
    Explanations

    numerical data or statistics related to various subjects

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_post_32k-oai
    Configuration
    jbloom/GPT2-Small-OAI-v5-32k-resid-post-SAEs/v5_32k_layer_8.pt
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    32,768
    Data Type
    torch.float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    standard
    Context Size
    64
    Dataset
    Skylion007/openwebtext
    Activation Function
    topk
    Embeds
    IFrame
    Link
    Neuron Alignment
    Index
    Value
    % of L₁
    109
    +0.11
    0.5%
    720
    +0.10
    0.5%
    638
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    326
    +0.11
    0.03
    373
    +0.10
    -0.01
    573
    +0.09
    0.02
    Negative Logits
    uesday
    -0.68
    iaries
    -0.66
    Else
    -0.64
    .?
    -0.64
    ukemia
    -0.60
    onday
    -0.60
    efeated
    -0.59
    >:
    -0.59
    endars
    -0.58
    irst
    -0.58
    POSITIVE LOGITS
    BuyableInstoreAndOnline
    0.69
    ãĥ«
    0.64
     ATK
    0.63
     Stamina
    0.62
    ãĥīãĥ©
    0.61
     Conquer
    0.60
     Damage
    0.59
    ãĤ©
    0.59
     kcal
    0.57
     VAL
    0.57
    Activations Density 0.096%

    No Known Activations