© 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. 9502
    Prev
    Next
    INDEX
    Explanations

    governmental institutions and official departments

    oai_token-act-pair · gpt-3.5-turbo

    references to governmental and law enforcement entities

    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
    ?",
    -0.68
    ?),
    -0.68
     predomin
    -0.64
    "))
    -0.60
    pired
    -0.59
    uably
    -0.58
    successfully
    -0.57
    )",
    -0.56
    efully
    -0.55
     enjoys
    -0.54
    POSITIVE LOGITS
    .
    1.08
    .'
    0.89
    .[
    0.87
     spokeswoman
    0.87
     spokesman
    0.86
     .
    0.86
    *.
    0.83
    .�
    0.83
    reports
    0.83
    .*
    0.80
    Activations Density 0.219%

    No Known Activations