© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. OpenAI · Sparse Autoencoder for GPT2-Small - v5 2024
    3. GPT2-Small
    4. Residual Post - 32k
    5. 10-RES_POST_32K-OAI
    6. 29541
    Prev
    Next
    INDEX
    Explanations

    references to community engagement and invitations for participation

    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
    464
    +0.17
    0.8%
    111
    +0.12
    0.5%
    74
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    49
    +0.17
    0.13
    718
    +0.12
    0.11
    551
    +0.12
    0.10
    Negative Logits
    pex
    -0.82
    illac
    -0.78
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    -0.76
    quickShipAvailable
    -0.73
    ©¶æ
    -0.70
    ttle
    -0.70
    yrim
    -0.69
    psc
    -0.67
    byss
    -0.67
     restrained
    -0.63
    POSITIVE LOGITS
     retweet
    1.04
     comment
    1.01
     chat
    0.99
     email
    0.92
     Tweet
    0.90
     Subscribe
    0.89
     Share
    0.89
     share
    0.89
     tweet
    0.88
     anonymously
    0.88
    Activations Density 1.111%

    No Known Activations