© 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. 30691
    Prev
    Next
    INDEX
    Explanations

    proper nouns and names of people or organizations

    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
    659
    +0.13
    0.6%
    3
    +0.12
    0.6%
    650
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    659
    +0.13
    0.14
    232
    +0.12
    0.12
    700
    +0.11
    0.11
    Negative Logits
     Flavoring
    -0.83
     recess
    -0.64
     Mandatory
    -0.64
     Fancy
    -0.63
     mono
    -0.62
    ģĸ
    -0.62
     compulsory
    -0.61
     lockout
    -0.59
     RAW
    -0.59
     arrests
    -0.59
    POSITIVE LOGITS
    mann
    1.62
    lein
    1.48
    meier
    1.42
    baum
    1.39
    bach
    1.35
    lander
    1.34
    lich
    1.33
    meyer
    1.33
    kamp
    1.31
    linger
    1.30
    Activations Density 1.359%

    No Known Activations