© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 12-RES-JB
    11. 5031
    Prev
    Next
    INDEX
    Explanations

    phrases related to the concept of actions or events happening

    oai_token-act-pair · gpt-3.5-turbo
    Triggered by @bot

    variations of the verb "come"

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 12-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_post
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    ļéĨĴ
    -0.84
    cius
    -0.81
    WER
    -0.74
    REC
    -0.74
    NOW
    -0.72
    icons
    -0.69
    raint
    -0.69
    guyen
    -0.68
    IVE
    -0.67
    neum
    -0.67
    POSITIVE LOGITS
     close
    1.10
     anywhere
    1.07
     cheaply
    1.03
     remotely
    1.02
     cheap
    1.01
     until
    0.91
     anymore
    0.86
     till
    0.84
     anytime
    0.82
     near
    0.77
    Activations Density 0.054%

    No Known Activations