© 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. 29397
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "mystery."

    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
    373
    +0.11
    0.5%
    672
    +0.10
    0.5%
    655
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.11
    0.04
    401
    +0.10
    0.03
    490
    +0.10
    0.02
    Negative Logits
    baugh
    -0.81
    erate
    -0.72
    olt
    -0.72
    chuk
    -0.70
    oji
    -0.69
    ornia
    -0.67
    ovie
    -0.66
    attery
    -0.66
    ewski
    -0.65
    minster
    -0.65
    POSITIVE LOGITS
     solved
    1.36
     surrounding
    1.02
     solving
    0.98
     unsolved
    0.97
     surrounds
    0.94
     mystery
    0.90
     puzzle
    0.84
     mysteries
    0.84
     unravel
    0.82
     puzzles
    0.80
    Activations Density 0.246%

    No Known Activations