© 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. 8-RES_POST_32K-OAI
    6. 5677
    Prev
    Next
    INDEX
    Explanations

    references to the letter 'g' in various contexts

    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
    240
    +0.14
    0.6%
    68
    +0.11
    0.5%
    489
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    659
    +0.14
    0.04
    174
    +0.11
    0.03
    569
    +0.10
    0.03
    Negative Logits
    CLASSIFIED
    -0.71
    e
    -0.71
    eer
    -0.71
    eers
    -0.69
    NESS
    -0.68
    BILITY
    -0.65
    TRUMP
    -0.65
    LEASE
    -0.65
    HAHA
    -0.65
     HIS
    -0.64
    POSITIVE LOGITS
    raphics
    1.10
    mt
    0.93
    raham
    0.91
    ordon
    0.89
    plot
    0.88
    uala
    0.88
    reens
    0.87
    uments
    0.87
    reek
    0.86
    ene
    0.85
    Activations Density 0.090%

    No Known Activations