© 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
    2. OpenAI · Sparse Autoencoder for GPT2-Small - v5 2024
    3. GPT2-Small
    4. Residual Post - 32k
    5. 10-RES_POST_32K-OAI
    6. 29689
    Prev
    Next
    INDEX
    Explanations

    specific names and details related to individuals and social media interactions

    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
    +0.13
    0.6%
    151
    +0.12
    0.6%
    586
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    406
    +0.13
    0.03
    563
    +0.12
    0.03
    293
    +0.10
    0.02
    Negative Logits
     Swordsman
    -0.80
    ntil
    -0.70
     Warrant
    -0.66
     unification
    -0.65
    ommel
    -0.64
    £ı
    -0.64
    olitan
    -0.63
    è¦ļéĨĴ
    -0.62
     Promise
    -0.62
     embodiments
    -0.60
    POSITIVE LOGITS
    \
    0.82
    \'
    0.79
    âĺ
    0.74
    \.
    0.74
    \">
    0.73
    âĸ
    0.73
    ¨
    0.71
    âĸĪâĸĪâĸĪâĸĪ
    0.70
    Ì
    0.70
    ~
    0.68
    Activations Density 0.164%

    No Known Activations