© 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. 21192
    Prev
    Next
    INDEX
    Explanations

    keywords related to publication, availability, acknowledgment, support, and funding

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to the availability and distribution of content or services

    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
     Others
    -0.66
    Others
    -0.63
    zers
    -0.63
    ses
    -0.61
    things
    -0.60
    rosso
    -0.60
     mistakes
    -0.59
     delays
    -0.59
     Blacks
    -0.58
     spikes
    -0.58
    POSITIVE LOGITS
     primarily
    0.95
     geographically
    0.94
     principally
    0.93
     solely
    0.83
     hereby
    0.83
     exclusively
    0.83
     chiefly
    0.82
     squarely
    0.80
     annually
    0.77
     mainly
    0.77
    Activations Density 0.250%

    No Known Activations