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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 30182
    Prev
    Next
    INDEX
    Explanations

    phrases indicating direction or consideration of various factors

    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
    611
    +0.12
    0.5%
    71
    +0.12
    0.5%
    374
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    608
    +0.12
    0.05
    611
    +0.12
    0.03
    569
    +0.11
    0.03
    Negative Logits
    lished
    -0.75
    ostic
    -0.67
    etitive
    -0.65
    riad
    -0.64
    etheless
    -0.63
     beginnings
    -0.62
    ivating
    -0.61
    ãĥĨ
    -0.61
    heast
    -0.60
    inguished
    -0.59
    POSITIVE LOGITS
     stride
    1.15
     granted
    0.95
     seriously
    0.75
     consideration
    0.74
     heart
    0.74
     hostage
    0.71
    Adds
    0.71
     Seriously
    0.70
     lightly
    0.69
     advis
    0.69
    Activations Density 0.387%

    No Known Activations