© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 22679
    Prev
    Next
    INDEX
    Explanations

    mentions of people's origins or residences

    oai_token-act-pair · gpt-3.5-turbo

    terms indicating specific identities or roles of individuals in a community

    oai_token-act-pair · gpt-4o-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
    EStreamFrame
    -0.73
    Plugin
    -0.69
     [];
    -0.69
    ÙIJ
    -0.68
    Request
    -0.68
    Translation
    -0.68
     ());
    -0.67
    Roaming
    -0.66
    OME
    -0.66
    FREE
    -0.65
    POSITIVE LOGITS
     extraord
    1.34
     Shaun
    1.17
     Nathan
    1.13
     Laura
    1.11
     Alex
    1.11
     Alan
    1.10
     Stephen
    1.10
     Richard
    1.10
     Jason
    1.10
     Keith
    1.10
    Activations Density 0.343%

    No Known Activations