© 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. 27552
    Prev
    Next
    INDEX
    Explanations

    terms related to intelligence and signaling, particularly within the context of organizations or systems

    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
    183
    +0.11
    0.5%
    659
    +0.11
    0.5%
    35
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    659
    +0.11
    0.03
    314
    +0.11
    -0.00
    284
    +0.11
    0.02
    Negative Logits
    etsk
    -0.77
     Cuomo
    -0.74
     Cassidy
    -0.73
     Gaddafi
    -0.68
     STATS
    -0.68
     Mub
    -0.67
     Bagg
    -0.66
     Clash
    -0.64
     Scope
    -0.63
    hift
    -0.63
    POSITIVE LOGITS
    urd
    1.20
    ourney
    1.20
    fried
    1.13
    mund
    1.06
    wered
    0.92
    mas
    0.91
    ils
    0.90
    rim
    0.90
    ldom
    0.89
    mare
    0.89
    Activations Density 0.153%

    No Known Activations