© 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. 30017
    Prev
    Next
    INDEX
    Explanations

    questions and inquiry-related phrases

    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
    273
    +0.13
    0.6%
    613
    +0.10
    0.4%
    350
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    6
    +0.13
    0.07
    640
    +0.10
    0.06
    107
    +0.09
    0.06
    Negative Logits
    morph
    -0.73
    pun
    -0.70
    fitting
    -0.67
    luaj
    -0.66
    interstitial
    -0.65
    estinal
    -0.65
    raint
    -0.64
    hood
    -0.64
    verages
    -0.64
    gettable
    -0.63
    POSITIVE LOGITS
    Q
    0.85
     Q
    0.80
    ANS
    0.74
    WD
    0.73
    MR
    0.71
     MR
    0.70
    A
    0.69
    AAF
    0.66
    Solution
    0.65
    ITNESS
    0.63
    Activations Density 0.544%

    No Known Activations