© 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. 29356
    Prev
    Next
    INDEX
    Explanations

    sequences of numerical and statistical data in a structured format

    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
    259
    +0.13
    0.6%
    461
    +0.10
    0.5%
    684
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    442
    +0.13
    0.07
    655
    +0.10
    0.06
    620
    +0.10
    0.04
    Negative Logits
    kas
    -0.80
     Flavoring
    -0.77
     OW
    -0.70
     @@
    -0.69
     Loaded
    -0.68
     datas
    -0.63
     Mods
    -0.63
     Vendor
    -0.61
     Shard
    -0.59
     Hi
    -0.59
    POSITIVE LOGITS
    ·
    1.14
    icter
    0.77
    âĢIJ
    0.76
    486
    0.75
    446
    0.74
    iac
    0.73
    lihood
    0.72
    IRD
    0.70
    346
    0.68
    ranging
    0.68
    Activations Density 0.430%

    No Known Activations