© 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. 29904
    Prev
    Next
    INDEX
    Explanations

    numerical statistics related to sports performance

    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
    +0.12
    0.5%
    21
    +0.10
    0.4%
    279
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    161
    +0.12
    0.03
    4
    +0.10
    0.04
    21
    +0.10
    0.03
    Negative Logits
    nesday
    -0.84
     thous
    -0.73
    eday
    -0.71
    azer
    -0.70
    aimon
    -0.67
    initely
    -0.65
    tons
    -0.65
    yg
    -0.64
     eleph
    -0.64
    culus
    -0.64
    POSITIVE LOGITS
    seed
    0.88
    HOME
    0.88
    Ranked
    0.70
    0
    0.67
    1
    0.67
    LOS
    0.65
     PROGRAM
    0.64
    mination
    0.63
    HEAD
    0.63
     DRAGON
    0.62
    Activations Density 0.410%

    No Known Activations