© 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. 20867
    Prev
    Next
    INDEX
    Explanations

    references to fiscal years

    oai_token-act-pair · gpt-3.5-turbo

    references to fiscal years and related budgetary discussions

    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
    href
    -0.67
    xual
    -0.67
    lain
    -0.67
    ipedia
    -0.64
    elling
    -0.64
    Magikarp
    -0.63
     Ves
    -0.63
    Pie
    -0.62
    ugen
    -0.62
     Jenner
    -0.62
    POSITIVE LOGITS
     cliff
    0.99
     prud
    0.83
     year
    0.82
     deficit
    0.82
     restraint
    0.81
     austerity
    0.80
     consolidation
    0.78
     stimulus
    0.77
     crisis
    0.75
    itures
    0.75
    Activations Density 0.032%

    No Known Activations