© 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. 27613
    Prev
    Next
    INDEX
    Explanations

    references to objects or items, particularly related to transport or storage contexts

    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
    71
    +0.11
    0.5%
    651
    +0.10
    0.4%
    20
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.11
    0.05
    352
    +0.10
    0.04
    678
    +0.09
    0.03
    Negative Logits
    ahi
    -0.87
    oi
    -0.77
    estate
    -0.76
    estro
    -0.74
    eton
    -0.73
    achu
    -0.73
    ed
    -0.72
    ento
    -0.71
    arios
    -0.71
    hof
    -0.70
    POSITIVE LOGITS
    wood
    0.73
     fumes
    0.72
     Stur
    0.72
    iously
    0.69
     lips
    0.65
     Seat
    0.64
     hold
    0.64
    keyes
    0.64
     seat
    0.63
     sway
    0.63
    Activations Density 0.273%

    No Known Activations