© 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. 9-RES-JB
    11. 24274
    Prev
    Next
    INDEX
    Explanations

    actions related to opening or revealing something

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "open" and its variations

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    Posted
    -0.71
     endors
    -0.68
    aea
    -0.67
    INO
    -0.64
    heres
    -0.63
    owicz
    -0.63
    ylum
    -0.61
     oblig
    -0.61
     nationwide
    -0.60
    ========
    -0.60
    POSITIVE LOGITS
    epad
    0.89
     headphones
    0.82
     Reload
    0.79
     blender
    0.78
     calculator
    0.77
     google
    0.75
     throttle
    0.75
     Photoshop
    0.74
     eyed
    0.73
     goggles
    0.71
    Activations Density 0.258%

    No Known Activations