Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 6-RES-JB
    6. 8248
    Prev
    Next
    INDEX
    Explanations

    references to extremely large monetary amounts, specifically in the trillions

    oai_token-act-pair · gpt-3.5-turbo

    references to large monetary values or costs, particularly in the trillions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ¶æ
    -0.70
    bable
    -0.68
    chester
    -0.68
     ANGEL
    -0.65
    drawn
    -0.63
     Gentle
    -0.62
    supp
    -0.62
     Char
    -0.62
    Hunt
    -0.61
     Clin
    -0.61
    POSITIVE LOGITS
     dollars
    1.01
    ython
    0.91
    dollar
    0.89
     dollar
    0.86
    abyte
    0.84
     trillion
    0.84
    undo
    0.83
    ulously
    0.82
     gallons
    0.82
     cubic
    0.82
    Activations Density 0.022%

    No Known Activations