© 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. 9-RES-JB
    11. 13484
    Prev
    Next
    INDEX
    Explanations

    words related to legal and administrative procedures

    oai_token-act-pair · gpt-3.5-turbo

    references to legal and procedural frameworks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    birds
    -0.71
    igl
    -0.67
    hiro
    -0.65
    ãĥ©ãĥ³
    -0.65
    azo
    -0.64
     Flavoring
    -0.61
    rill
    -0.60
    mson
    -0.60
    stocks
    -0.58
    ku
    -0.58
    POSITIVE LOGITS
    ional
    1.02
     procedures
    0.90
     procedure
    0.83
     overseen
    0.82
     Procedure
    0.80
     instituted
    0.77
     governing
    0.76
    DragonMagazine
    0.75
     process
    0.74
     proceedings
    0.74
    Activations Density 0.083%

    No Known Activations