© 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. 30912
    Prev
    Next
    INDEX
    Explanations

    instances of the word "resilience" and its variants

    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
    385
    +0.11
    0.5%
    354
    +0.09
    0.4%
    274
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    659
    +0.11
    0.05
    461
    +0.09
    0.02
    232
    +0.09
    0.03
    Negative Logits
    theless
    -0.75
    alty
    -0.73
    rant
    -0.73
     Morg
    -0.67
    rification
    -0.65
    rend
    -0.65
    rals
    -0.64
    lish
    -0.63
     Pluto
    -0.63
    raper
    -0.62
    POSITIVE LOGITS
    us
    0.85
    angelo
    0.83
    iffe
    0.81
    OUS
    0.80
     Sturgeon
    0.78
    iquid
    0.77
    onga
    0.76
    utic
    0.74
    ño
    0.72
    Äĩ
    0.71
    Activations Density 0.341%

    No Known Activations