© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenAI · Sparse Autoencoder for GPT2-Small - v5 2024
    5. GPT2-Small
    7. Residual Post - 32k
    9. 8-RES_POST_32K-OAI
    11. 6682
    Prev
    Next
    INDEX
    Explanations

    references to the name "Az."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_post_32k-oai
    Configuration
    jbloom/GPT2-Small-OAI-v5-32k-resid-post-SAEs/v5_32k_layer_8.pt
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    32,768
    Data Type
    torch.float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    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
    377
    +0.14
    0.6%
    755
    +0.12
    0.6%
    662
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    659
    +0.14
    0.01
    365
    +0.12
    0.01
    755
    +0.12
    0.01
    Negative Logits
    bered
    -0.76
    hift
    -0.67
    RANT
    -0.64
    LINE
    -0.64
    lihood
    -0.62
    started
    -0.62
     Dough
    -0.61
    baugh
    -0.61
    nesday
    -0.59
     externalToEVAOnly
    -0.58
    POSITIVE LOGITS
    ļ
    0.87
    zona
    0.86
    azel
    0.82
    isance
    0.78
    vertis
    0.77
    Ĭ
    0.77
    unci
    0.76
    é¾įåĸļ士
    0.73
    illary
    0.73
    ãĥ£
    0.72
    Activations Density 0.029%

    No Known Activations