© 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. 10265
    Prev
    Next
    INDEX
    Explanations

    mentions related to specific entities and organizations

    oai_token-act-pair · gpt-3.5-turbo

    references to organizations and their activities

    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
     crap
    -0.68
    arget
    -0.67
     jurisdiction
    -0.65
    Bec
    -0.65
    BILL
    -0.64
     subpoena
    -0.63
    Required
    -0.62
    xon
    -0.62
    draft
    -0.61
    Reading
    -0.60
    POSITIVE LOGITS
     commented
    1.28
     thanked
    1.23
     spokesperson
    1.20
     tweeted
    1.19
     stressed
    1.17
     insists
    1.17
     spokesman
    1.16
     joked
    1.14
     said
    1.14
     refuted
    1.14
    Activations Density 1.342%

    No Known Activations