© 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
    3. OpenAI · Sparse Autoencoder for GPT2-Small - v5 2024
    5. GPT2-Small
    7. Residual Post - 32k
    9. 10-RES_POST_32K-OAI
    11. 29724
    Prev
    Next
    INDEX
    Explanations

    numeric values, particularly those that appear in a structured or coded format

    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
    314
    +0.14
    0.6%
    373
    +0.11
    0.5%
    107
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    326
    +0.14
    0.04
    316
    +0.11
    0.04
    565
    +0.10
    0.03
    Negative Logits
     creeps
    -0.69
     Xan
    -0.67
     cooled
    -0.66
     OM
    -0.65
     neigh
    -0.65
     α
    -0.65
     interpreting
    -0.64
     Mono
    -0.63
     Combine
    -0.63
     Parad
    -0.62
    POSITIVE LOGITS
    20439
    1.26
    qs
    1.07
    tnc
    1.02
    mb
    1.02
    committee
    1.01
    shared
    1.01
    sports
    1.01
    days
    1.00
    df
    0.99
    fc
    0.98
    Activations Density 0.396%

    No Known Activations