© 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. 8-RES_POST_32K-OAI
    11. 6052
    Prev
    Next
    INDEX
    Explanations

    words starting with the letters 'ob', 'ol', 'ir', 'ur', 'ub', 'qu', and various other letter combinations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_post_32k-oai
    Configuration
    jbloom/GPT2-Small-OAI-v5-32k-resid-post-SAEs/v5_32k_layer_8.pt
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    32,768
    Data Type
    torch.float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    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
    736
    +0.12
    0.6%
    548
    +0.10
    0.5%
    161
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    232
    +0.12
    0.08
    659
    +0.10
    0.07
    284
    +0.10
    0.05
    Negative Logits
     [&
    -0.70
     âĢ¦"
    -0.68
    Magikarp
    -0.67
    /-
    -0.65
     ..."
    -0.65
    eers
    -0.65
    xual
    -0.65
     è£ı
    -0.64
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    -0.64
     respectively
    -0.61
    POSITIVE LOGITS
    imar
    0.92
    endish
    0.92
    istar
    0.79
    adena
    0.78
    atown
    0.78
    ippery
    0.74
    ford
    0.74
    isl
    0.69
    ashtra
    0.68
    sonian
    0.68
    Activations Density 0.414%

    No Known Activations