© 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 EvalsExportsinterp-engineNEWAPI 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. 27198
    Prev
    Next
    INDEX
    Explanations

    words indicating concern or variability in opinions about environmental issues

    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
    512
    +0.10
    0.4%
    690
    +0.09
    0.4%
    575
    +0.08
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    314
    +0.10
    0.00
    283
    +0.09
    0.02
    575
    +0.08
    0.05
    Negative Logits
     QR
    -0.71
    cells
    -0.68
     Abedin
    -0.68
     Suk
    -0.67
     sclerosis
    -0.65
    BSD
    -0.63
    ãĥ¼ãĥĨ
    -0.61
     Spur
    -0.60
    UFC
    -0.60
     BMC
    -0.58
    POSITIVE LOGITS
    hat
    1.60
    here
    1.47
    orld
    1.12
    herer
    1.07
    heres
    1.01
    ently
    0.98
    aining
    0.95
    ained
    0.94
    ruck
    0.91
    weet
    0.90
    Activations Density 0.278%

    No Known Activations