© 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. 11-RES-JB
    11. 5192
    Prev
    Next
    INDEX
    Explanations

    keywords related to political figures ('Bre') and their names

    oai_token-act-pair · gpt-3.5-turbo
    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
    lessly
    -0.75
    iating
    -0.70
     terr
    -0.69
    iated
    -0.67
     numbered
    -0.65
    ONES
    -0.64
     Wolfgang
    -0.63
     Fired
    -0.60
    DEV
    -0.57
    iates
    -0.56
    POSITIVE LOGITS
    thren
    1.57
    itbart
    1.33
    vity
    1.26
    vard
    1.21
    akers
    1.09
    eding
    1.09
    ton
    1.08
    cht
    1.08
    AKING
    1.03
    tsky
    1.03
    Activations Density 0.022%

    No Known Activations