© 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. 31338
    Prev
    Next
    INDEX
    Explanations

    words related to structural integrity and related concepts

    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
    302
    +0.09
    0.4%
    269
    +0.09
    0.4%
    288
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.09
    0.04
    314
    +0.09
    -0.00
    588
    +0.09
    0.03
    Negative Logits
     Reborn
    -0.69
     foremost
    -0.66
     Leone
    -0.65
     Ness
    -0.63
     Passage
    -0.62
    nder
    -0.62
    ça
    -0.59
    nea
    -0.58
    zig
    -0.58
    anders
    -0.58
    POSITIVE LOGITS
    uring
    1.35
    ures
    1.34
    ured
    1.26
    urally
    1.25
    ural
    1.17
    urable
    1.03
    urated
    0.98
    URE
    0.95
    URES
    0.95
    ible
    0.94
    Activations Density 0.171%

    No Known Activations