© 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. 10-RES-JB
    11. 2893
    Prev
    Next
    INDEX
    Explanations

    references to specific financial institutions, particularly banks

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "bank of" in different contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    vp
    -0.77
    blance
    -0.73
     pronouns
    -0.68
    href
    -0.68
    mble
    -0.65
     lapt
    -0.64
     toile
    -0.63
    bsite
    -0.62
     flashbacks
    -0.62
    picture
    -0.61
    POSITIVE LOGITS
     America
    0.92
     Cyprus
    0.85
     AMERICA
    0.84
     Americas
    0.83
     England
    0.82
     Ireland
    0.81
     Montreal
    0.81
    America
    0.80
     Tokyo
    0.80
     Merrill
    0.78
    Activations Density 0.025%

    No Known Activations