© 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. 4-RES-JB
    11. 22259
    Prev
    Next
    INDEX
    Explanations

    instances of the word "pay" and related terms, specifically related to financial transactions

    oai_token-act-pair · gpt-3.5-turbo

    verbs and phrases that indicate actions or states related to daily life and personal choices

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

    No Comments

    Negative Logits
     NEO
    -0.62
     Bene
    -0.58
     Nanto
    -0.57
     Directorate
    -0.50
     embedded
    -0.50
     summed
    -0.50
     ACPI
    -0.49
     concerned
    -0.48
     uniquely
    -0.48
     adopted
    -0.47
    POSITIVE LOGITS
    quit
    0.69
    bows
    0.68
    livion
    0.65
    levels
    0.61
    stocks
    0.58
    illions
    0.57
    bats
    0.56
    mails
    0.56
    gil
    0.56
    mop
    0.56
    Activations Density 1.477%

    No Known Activations