© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 29130
    Prev
    Next
    INDEX
    Explanations

    contractions and forms of the verb "to be."

    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
    685
    +0.12
    0.5%
    387
    +0.10
    0.5%
    267
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    551
    +0.12
    0.09
    49
    +0.10
    0.08
    685
    +0.10
    0.05
    Negative Logits
     discrep
    -0.69
    nob
    -0.67
    RANT
    -0.67
    Unknown
    -0.66
     outweigh
    -0.66
     outwe
    -0.64
    hed
    -0.62
    ufficient
    -0.59
    Newsletter
    -0.59
    laim
    -0.58
    POSITIVE LOGITS
     suppose
    1.01
     imagine
    0.80
     assume
    0.80
     look
    0.79
     Suppose
    0.79
     pretend
    0.79
     Compare
    0.74
     recap
    0.73
     summarize
    0.73
     visualize
    0.70
    Activations Density 0.347%

    No Known Activations