© 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. 10-RES_POST_32K-OAI
    11. 30662
    Prev
    Next
    INDEX
    Explanations

    elements of programming syntax or mathematical expressions

    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
    689
    +0.12
    0.5%
    166
    +0.10
    0.4%
    677
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    308
    +0.12
    0.03
    479
    +0.10
    0.01
    176
    +0.10
    0.01
    Negative Logits
    yt
    -0.68
    zbollah
    -0.66
    enegger
    -0.65
    ItemImage
    -0.63
    bourg
    -0.63
    riott
    -0.60
    eston
    -0.59
    onis
    -0.59
     rul
    -0.56
    liv
    -0.55
    POSITIVE LOGITS
     A
    2.14
    A
    1.50
     An
    1.40
     Ae
    1.07
     AJ
    1.06
     AB
    1.04
     B
    0.96
     AN
    0.95
     AA
    0.94
    AE
    0.92
    Activations Density 2.654%

    No Known Activations