© 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. 7-RES-JB
    11. 14242
    Prev
    Next
    INDEX
    Explanations

    phrases related to business operations and announcements

    oai_token-act-pair · gpt-3.5-turbo

    actions and plans related to business operations and communications

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    Downloadha
    -0.77
     allegedly
    -0.73
     Adolf
    -0.67
     blamed
    -0.65
     supposedly
    -0.62
     purportedly
    -0.61
     belonged
    -0.61
     ousted
    -0.60
     tainted
    -0.59
     overshadowed
    -0.59
    POSITIVE LOGITS
     ourselves
    1.43
     our
    0.92
     myself
    0.90
     Patreon
    0.86
    ilial
    0.77
    poke
    0.74
    atform
    0.70
     publish
    0.70
     sourcing
    0.67
    lished
    0.66
    Activations Density 0.779%

    No Known Activations