© 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. 29937
    Prev
    Next
    INDEX
    Explanations

    cooking instructions, particularly those involving adding ingredients

    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
    678
    +0.12
    0.5%
    52
    +0.10
    0.5%
    656
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    678
    +0.12
    0.04
    555
    +0.10
    0.03
    487
    +0.10
    0.02
    Negative Logits
    furt
    -0.73
    dayName
    -0.72
    opes
    -0.67
    pub
    -0.65
    utton
    -0.64
    Hunt
    -0.61
    issue
    -0.61
    worn
    -0.61
    fit
    -0.60
    eur
    -0.60
    POSITIVE LOGITS
     enough
    0.98
     chopped
    0.88
     ½
    0.87
     remaining
    0.83
    enough
    0.81
     sufficient
    0.79
     powdered
    0.76
     plenty
    0.76
     milk
    0.75
     boiling
    0.75
    Activations Density 0.191%

    No Known Activations