© 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. 29835
    Prev
    Next
    INDEX
    Explanations

    code-related terms and programming constructs

    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
    463
    +0.15
    0.7%
    409
    +0.11
    0.5%
    373
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    78
    +0.15
    0.03
    717
    +0.11
    0.03
    463
    +0.11
    0.03
    Negative Logits
    steen
    -0.78
     Goldstein
    -0.70
    ango
    -0.69
    ricks
    -0.69
    agog
    -0.69
     Cosponsors
    -0.68
    sung
    -0.67
     Homs
    -0.67
    yang
    -0.66
    burgh
    -0.65
    POSITIVE LOGITS
    /
    0.93
    / 
    0.81
    /)
    0.73
    /-
    0.72
    ascript
    0.70
    )/
    0.70
    /,
    0.70
     /
    0.68
    ///
    0.67
    via
    0.66
    Activations Density 0.374%

    No Known Activations