© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 1-RES-JB
    6. 15866
    Prev
    Next
    INDEX
    Explanations

    keywords related to banking and financial institutions

    oai_token-act-pair · gpt-3.5-turbo

    references to financial institutions and banking terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Horton
    -0.74
     cause
    -0.68
     Flavoring
    -0.65
     Dangerous
    -0.64
     Warm
    -0.63
     Inquisitor
    -0.63
    IVES
    -0.62
     Eisenhower
    -0.61
    IV
    -0.61
     Mile
    -0.61
    POSITIVE LOGITS
    bank
    1.39
    banks
    1.11
    Bank
    0.98
    rupt
    0.98
    sters
    0.98
    ular
    0.87
    tenance
    0.86
    cipled
    0.86
    rarily
    0.85
     banker
    0.82
    Activations Density 0.006%

    No Known Activations