© 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. 28038
    Prev
    Next
    INDEX
    Explanations

    variations of dashes or horizontal lines used for separation or decoration in text

    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
    274
    +0.12
    0.6%
    373
    +0.12
    0.6%
    314
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    314
    +0.12
    -0.01
    446
    +0.12
    0.01
    607
    +0.12
    0.02
    Negative Logits
     Lauder
    -0.74
     Constantin
    -0.73
     ILCS
    -0.72
     Scotia
    -0.68
     Clancy
    -0.68
     wed
    -0.67
     astronaut
    -0.65
     Nile
    -0.65
     Vie
    -0.64
     purse
    -0.63
    POSITIVE LOGITS
    -+
    1.44
    -|
    1.39
    ->
    1.04
    +
    1.00
    ==
    0.98
    ===
    0.98
    ľ
    0.96
    DOWN
    0.94
    +)
    0.91
    ||
    0.90
    Activations Density 0.219%

    No Known Activations