© 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. 29265
    Prev
    Next
    INDEX
    Explanations

    mentions of statistical effects and comparisons in research contexts

    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
    503
    +0.12
    0.5%
    222
    +0.10
    0.5%
    314
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    314
    +0.12
    -0.04
    167
    +0.10
    -0.01
    365
    +0.10
    0.00
    Negative Logits
     Fukushima
    -0.59
     misc
    -0.59
     fragrance
    -0.58
     wearer
    -0.57
     Bounty
    -0.57
    apixel
    -0.57
     Arduino
    -0.56
     Sochi
    -0.55
     skelet
    -0.55
     Nasa
    -0.55
    POSITIVE LOGITS
     versus
    0.94
    -,
    0.92
     equivalents
    0.85
    ueless
    0.82
     minus
    0.81
    +.
    0.79
    centric
    0.78
    -.
    0.78
    +,
    0.74
     versa
    0.73
    Activations Density 7.716%

    No Known Activations