© 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 EvalsExportsinterp-engineNEWAPI 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. 32214
    Prev
    Next
    INDEX
    Explanations

    instances of personal experiences or testimonials related to hardship or adversity

    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
    22
    +0.11
    0.5%
    544
    +0.11
    0.5%
    416
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    479
    +0.11
    0.02
    308
    +0.11
    0.05
    6
    +0.11
    0.16
    Negative Logits
     seiz
    -1.04
     Siren
    -0.96
     Venus
    -0.89
     Zeal
    -0.87
     helium
    -0.84
     iod
    -0.82
     orb
    -0.81
     seism
    -0.80
    olis
    -0.78
    ZE
    -0.77
    POSITIVE LOGITS
    Mc
    2.75
     Mc
    2.34
     McC
    1.85
     McG
    1.85
    McC
    1.83
     McN
    1.82
     McK
    1.82
     McCl
    1.82
     McD
    1.81
     McInt
    1.80
    Activations Density 8.622%

    No Known Activations