© 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
    2. OpenAI · Sparse Autoencoder for GPT2-Small - v5 2024
    3. GPT2-Small
    4. Residual Post - 32k
    5. 10-RES_POST_32K-OAI
    6. 28129
    Prev
    Next
    INDEX
    Explanations

    terminology related to newsletter subscriptions and user verification processes

    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
    +0.12
    0.6%
    560
    +0.10
    0.5%
    684
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    373
    +0.12
    -0.01
    211
    +0.10
    0.01
    508
    +0.10
    0.01
    Negative Logits
     contag
    -0.72
    itton
    -0.70
    mort
    -0.69
    rador
    -0.67
     sqor
    -0.66
    ntil
    -0.66
    endi
    -0.63
    itent
    -0.62
    istant
    -0.62
    rouse
    -0.61
    POSITIVE LOGITS
    \<
    0.68
    ItemImage
    0.67
    zens
    0.64
     Cancel
    0.63
    Newsletter
    0.63
     fewer
    0.61
    jac
    0.61
    Stars
    0.61
     Zup
    0.60
    stars
    0.59
    Activations Density 0.065%

    No Known Activations