© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 0-RES-JB
    11. 22256
    Prev
    Next
    INDEX
    Explanations

    references to specific stock market symbols and names

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of specific abbreviations or acronyms related to organizations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    orie
    -0.73
    inventoryQuantity
    -0.66
    business
    -0.64
    Flor
    -0.64
    Rose
    -0.64
    sections
    -0.64
    wolf
    -0.62
     Jericho
    -0.62
    Label
    -0.62
    merce
    -0.61
    POSITIVE LOGITS
    UAL
    2.72
    rish
    2.30
    uo
    1.98
    umar
    1.33
    imir
    1.31
    coni
    1.22
     antip
    1.02
     Cove
    1.01
    ugu
    0.97
    QU
    0.96
    Activations Density 0.049%

    No Known Activations