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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 11-RES-JB
    11. 3205
    Prev
    Next
    INDEX
    Explanations

    words related to finance and legal matters, such as inventory, incentives, merger, and money laundering

    oai_token-act-pair · gpt-3.5-turbo

    phrases and concepts related to economic and social policies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    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
     Boone
    -0.87
     Philly
    -0.78
     Betsy
    -0.71
     kickoff
    -0.70
     dudes
    -0.69
     JFK
    -0.69
     Brandon
    -0.67
     Belichick
    -0.67
     Paleo
    -0.66
     tornado
    -0.65
    POSITIVE LOGITS
    âĢ
    1.62
     âĢ
    1.33
     âĶ
    1.20
    ãĢ
    1.20
    .�
    1.14
     «
    1.03
    ¨
    1.03
    «
    0.99
    .(
    0.96
    Â
    0.95
    Activations Density 0.648%

    No Known Activations