© 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. 12569
    Prev
    Next
    INDEX
    Explanations

    references to government policies and procedures

    oai_token-act-pair · gpt-3.5-turbo

    references to research funding and disclosure information

    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
     booze
    -0.84
    ãĥĺ
    -0.83
     maybe
    -0.78
     nowhere
    -0.75
     kinda
    -0.75
    whatever
    -0.75
     gigs
    -0.75
    something
    -0.74
    ebook
    -0.74
     somehow
    -0.74
    POSITIVE LOGITS
     following
    1.21
     Subcommittee
    1.20
     foregoing
    1.09
     Comprehensive
    1.07
     Selected
    1.01
     Advisory
    1.00
     Committee
    1.00
     Sponsor
    1.00
     Annual
    0.98
     Continuing
    0.97
    Activations Density 0.462%

    No Known Activations