© 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. 2619
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal and criminal proceedings, such as charges, lawyers, and court outcomes

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    mentions of family members and legal representatives in relation to legal cases

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

    No Comments

    Negative Logits
    uggle
    -0.75
    twitch
    -0.68
    vertising
    -0.66
    iggle
    -0.66
    illary
    -0.66
    vantage
    -0.65
    okers
    -0.65
    utenberg
    -0.65
    uters
    -0.63
    fw
    -0.63
    POSITIVE LOGITS
     Gerry
    0.90
     Roger
    0.90
     Jorge
    0.89
     Nathaniel
    0.89
     Richard
    0.88
     Randy
    0.88
     Andrew
    0.88
     Christine
    0.87
     Noel
    0.86
     Marvin
    0.86
    Activations Density 0.282%

    No Known Activations