© 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. 8-RES_POST_32K-OAI
    11. 5668
    Prev
    Next
    INDEX
    Explanations

    proper nouns, particularly names of individuals and organizations

    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
    712
    +0.13
    0.6%
    666
    +0.10
    0.5%
    449
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    659
    +0.13
    0.14
    232
    +0.10
    0.10
    314
    +0.10
    -0.00
    Negative Logits
     showc
    -0.64
     Brav
    -0.63
    aceae
    -0.62
     Hornets
    -0.62
    Compat
    -0.57
    ccording
    -0.57
     Volks
    -0.57
     Ves
    -0.56
     Centauri
    -0.56
     Glac
    -0.55
    POSITIVE LOGITS
     Jr
    1.11
     Sr
    0.82
    nr
    0.82
    Jr
    0.75
    ensis
    0.75
     III
    0.74
     aka
    0.73
     PhD
    0.67
    inguished
    0.67
    icum
    0.67
    Activations Density 0.815%

    No Known Activations