© 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. 28801
    Prev
    Next
    INDEX
    Explanations

    occurrences of the article 'a' in various contexts

    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
    8
    +0.10
    0.5%
    756
    +0.10
    0.5%
    626
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    36
    +0.10
    0.13
    362
    +0.10
    0.10
    393
    +0.10
    0.09
    Negative Logits
    pton
    -1.00
    mb
    -0.75
    avorite
    -0.72
    eden
    -0.71
    olina
    -0.71
    asley
    -0.70
    Featured
    -0.70
     Famous
    -0.70
    aters
    -0.69
    astrous
    -0.69
    POSITIVE LOGITS
     celebration
    0.94
     collection
    0.85
     gimmick
    0.84
     hobby
    0.84
     exploration
    0.84
     glor
    0.83
     continuation
    0.82
     annoyance
    0.82
     standalone
    0.82
     reflection
    0.81
    Activations Density 0.727%

    No Known Activations