© 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. 29601
    Prev
    Next
    INDEX
    Explanations

    references to measurements or indicators of quality and quantity

    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
    21
    +0.12
    0.6%
    657
    +0.09
    0.4%
    476
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    232
    +0.12
    0.03
    373
    +0.09
    -0.03
    476
    +0.09
    0.01
    Negative Logits
    ãĥ¯ãĥ³
    -0.70
    ourn
    -0.68
    HAM
    -0.68
    RANT
    -0.67
    esan
    -0.67
    âĸĪâĸĪ
    -0.65
    lect
    -0.65
    uala
    -0.64
    enough
    -0.64
    gew
    -0.62
    POSITIVE LOGITS
     Healer
    0.63
    owered
    0.60
     Lens
    0.60
     --------
    0.58
     Translation
    0.58
     Norn
    0.57
     Color
    0.57
     Spirits
    0.56
     Illusion
    0.54
     Belt
    0.53
    Activations Density 0.256%

    No Known Activations