© 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. 20468
    Prev
    Next
    INDEX
    Explanations

    academic citations, references, and publication information

    oai_token-act-pair · gpt-3.5-turbo

    punctuation and citation formats

    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
    ļéĨĴ
    -0.75
     glim
    -0.69
     thous
    -0.63
     exha
    -0.62
     proble
    -0.61
     councill
    -0.60
     citiz
    -0.59
     pierced
    -0.59
     backlog
    -0.58
     stranded
    -0.58
    POSITIVE LOGITS
    1997
    1.93
    2006
    1.93
    1998
    1.92
    1993
    1.91
    1991
    1.91
    2004
    1.90
    1999
    1.90
    2005
    1.90
    1996
    1.90
    2009
    1.90
    Activations Density 0.094%

    No Known Activations