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. 4-RES-JB
    6. 12797
    Prev
    Next
    INDEX
    Explanations

    mentions of financial figures, specifically in the millions

    oai_token-act-pair · gpt-3.5-turbo

    references to monetary amounts, specifically in millions

    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
    alogue
    -0.78
    comes
    -0.73
    abulary
    -0.71
     Hast
    -0.69
    ivity
    -0.67
    anwhile
    -0.67
    alys
    -0.66
    nect
    -0.66
    osen
    -0.66
    anical
    -0.65
    POSITIVE LOGITS
     dollars
    1.26
     euros
    1.01
     dollar
    0.93
     bucks
    0.88
    -$
    0.87
     (£
    0.84
     pounds
    0.83
    $$$$
    0.83
     Dollars
    0.83
     increments
    0.81
    Activations Density 0.045%

    No Known Activations