© 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. 26548
    Prev
    Next
    INDEX
    Explanations

    references to articles and reports

    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
    756
    +0.12
    0.5%
    360
    +0.10
    0.5%
    655
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    679
    +0.12
    0.03
    655
    +0.10
    0.02
    452
    +0.09
    0.02
    Negative Logits
    cffff
    -0.91
    cffffcc
    -0.80
     Nadu
    -0.76
    ersen
    -0.75
    pter
    -0.72
    NetMessage
    -0.70
    cipled
    -0.69
    ²¾
    -0.69
    uits
    -0.68
    illet
    -0.67
    POSITIVE LOGITS
    meal
    1.02
    orial
    0.94
    velop
    0.77
     detailing
    0.75
     published
    0.74
    iversary
    0.70
     titled
    0.69
    WR
    0.68
    arians
    0.68
    abul
    0.68
    Activations Density 0.142%

    No Known Activations