© 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. 30107
    Prev
    Next
    INDEX
    Explanations

    references to images and calls to action for support and engagement

    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
    373
    +0.14
    0.6%
    519
    +0.10
    0.4%
    505
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    373
    +0.14
    -0.01
    755
    +0.10
    0.01
    211
    +0.09
    0.00
    Negative Logits
     abound
    -0.74
     IMAGES
    -0.66
     discouraged
    -0.66
     ado
    -0.65
    dylib
    -0.60
    enance
    -0.57
     widow
    -0.57
     transcripts
    -0.57
    eatures
    -0.57
     wound
    -0.56
    POSITIVE LOGITS
    ãĥĦ
    0.82
    ighty
    0.78
    éĸ
    0.77
    ãĥ¯ãĥ³
    0.76
    ©¶æ
    0.73
    è¦ļéĨĴ
    0.72
    ixty
    0.69
    need
    0.68
    20439
    0.67
    人
    0.66
    Activations Density 0.200%

    No Known Activations