© 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. 5690
    Prev
    Next
    INDEX
    Explanations

    pronouns that refer to groups of people or objects

    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
    580
    +0.09
    0.4%
    354
    +0.09
    0.4%
    762
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    762
    +0.09
    0.06
    241
    +0.09
    0.04
    580
    +0.09
    0.04
    Negative Logits
     Megan
    -0.60
     KC
    -0.60
     LH
    -0.59
     Geek
    -0.57
    CCC
    -0.57
     Dian
    -0.56
     Salon
    -0.56
    âĢ¢âĢ¢
    -0.56
     Lane
    -0.55
     FX
    -0.55
    POSITIVE LOGITS
    selves
    1.83
    atically
    1.57
     selves
    1.56
    atic
    1.36
    self
    1.28
    ovie
    0.99
     themselves
    0.94
    're
    0.89
    ilitary
    0.89
     individually
    0.88
    Activations Density 0.221%

    No Known Activations