© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 30905
    Prev
    Next
    INDEX
    Explanations

    phrases that express risk or danger

    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
    451
    +0.11
    0.5%
    207
    +0.10
    0.5%
    488
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    608
    +0.11
    0.10
    172
    +0.10
    0.06
    408
    +0.10
    0.11
    Negative Logits
     Cosponsors
    -0.83
     Practices
    -0.75
    Premium
    -0.72
     guiName
    -0.72
    TEXTURE
    -0.71
     GOODMAN
    -0.69
    DragonMagazine
    -0.69
     ECO
    -0.69
    ept
    -0.67
     guiIcon
    -0.66
    POSITIVE LOGITS
     annihilation
    1.50
     ruin
    1.49
     disaster
    1.49
     extinction
    1.47
     catastrophe
    1.39
     doom
    1.39
     demise
    1.36
     destruction
    1.34
     death
    1.32
     downfall
    1.32
    Activations Density 1.608%

    No Known Activations