© 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. 29028
    Prev
    Next
    INDEX
    Explanations

    instances of the word "main" and its variations in the context of primary subjects or topics

    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
    314
    +0.15
    0.7%
    459
    +0.12
    0.5%
    457
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    623
    +0.15
    0.02
    8
    +0.12
    0.02
    752
    +0.10
    0.03
    Negative Logits
    ocene
    -0.78
     [];
    -0.64
    ":[
    -0.63
     firsthand
    -0.60
     Remastered
    -0.59
     Ratio
    -0.57
     Gael
    -0.57
    terday
    -0.57
     Tycoon
    -0.57
    olation
    -0.56
    POSITIVE LOGITS
    stay
    1.55
    frame
    1.45
    tenance
    1.33
    stream
    1.16
    tan
    1.15
    frames
    1.15
    mast
    1.10
    stem
    1.07
    deck
    1.04
    ten
    1.02
    Activations Density 0.078%

    No Known Activations