© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 10-RES_POST_32K-OAI
    11. 29946
    Prev
    Next
    INDEX
    Explanations

    the presence of names or entities associated with the term "endor."

    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
    583
    +0.13
    0.6%
    398
    +0.10
    0.5%
    412
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    659
    +0.13
    0.08
    232
    +0.10
    0.08
    284
    +0.10
    0.05
    Negative Logits
    staking
    -0.74
    ocre
    -0.69
    laws
    -0.68
    UNE
    -0.66
    agraph
    -0.66
    ulus
    -0.62
    Enough
    -0.62
     Lup
    -0.62
    unes
    -0.62
    onest
    -0.61
    POSITIVE LOGITS
    ger
    1.07
    gh
    0.93
    ffer
    0.88
    ds
    0.85
    de
    0.83
    ff
    0.83
    cher
    0.82
    tz
    0.81
    cer
    0.80
    lde
    0.79
    Activations Density 0.764%

    No Known Activations