© 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. 4-RES-JB
    6. 20416
    Prev
    Next
    INDEX
    Explanations

    mentions of specific amounts of money

    oai_token-act-pair · gpt-3.5-turbo

    monetary figures or amounts

    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
    sole
    -0.72
    warts
    -0.69
     Aval
    -0.67
    bread
    -0.67
    ournal
    -0.64
    agn
    -0.64
     Synd
    -0.63
    osen
    -0.63
    rival
    -0.62
    soType
    -0.61
    POSITIVE LOGITS
    -$
    1.17
     (£
    0.88
    /$
    0.86
     dollars
    0.85
     apiece
    0.84
     gp
    0.81
     euros
    0.81
    gp
    0.80
     USD
    0.79
    ledged
    0.79
    Activations Density 0.054%

    No Known Activations