© 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. 26869
    Prev
    Next
    INDEX
    Explanations

    words with the substring "ri" or similar variations

    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
    497
    +0.14
    0.7%
    265
    +0.10
    0.4%
    21
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    314
    +0.14
    -0.01
    284
    +0.10
    0.03
    374
    +0.09
    -0.01
    Negative Logits
    vier
    -0.74
    ither
    -0.68
    naires
    -0.68
    nesses
    -0.66
    alde
    -0.64
    ings
    -0.62
    iley
    -0.62
    lf
    -0.61
    leep
    -0.59
    mble
    -0.59
    POSITIVE LOGITS
    arch
    1.00
    archy
    0.94
    archs
    0.81
    ZI
    0.74
    onial
    0.74
    ony
    0.73
    zeb
    0.69
    ONS
    0.68
    ARCH
    0.67
    onite
    0.66
    Activations Density 0.524%

    No Known Activations