© 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. 29842
    Prev
    Next
    INDEX
    Explanations

    mentions of artificial intelligence and its implications

    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
    721
    +0.11
    0.5%
    566
    +0.11
    0.5%
    759
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.11
    0.02
    57
    +0.11
    0.01
    17
    +0.10
    0.01
    Negative Logits
    lain
    -0.97
    adoes
    -0.88
    ados
    -0.82
    ning
    -0.80
    cake
    -0.74
    ingen
    -0.73
    atin
    -0.72
    ned
    -0.69
    ado
    -0.68
    lie
    -0.67
    POSITIVE LOGITS
    venture
    0.71
    Heart
    0.70
    Bs
    0.69
    Eva
    0.68
    Reference
    0.67
    GEN
    0.65
    ura
    0.65
    ersion
    0.65
    WB
    0.63
     Controlled
    0.63
    Activations Density 0.094%

    No Known Activations