© 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. 0-RES-JB
    11. 11285
    Prev
    Next
    INDEX
    Explanations

    financial figures in billions

    oai_token-act-pair · gpt-3.5-turbo

    financial figures and monetary values

    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
     agitation
    -0.66
     whipped
    -0.62
     demeanor
    -0.62
     mustache
    -0.61
     gall
    -0.61
     swings
    -0.60
     Swing
    -0.60
     leveled
    -0.60
     setup
    -0.60
     molded
    -0.59
    POSITIVE LOGITS
    bn
    4.15
    BN
    2.03
    billion
    1.79
    tn
    1.74
     billion
    1.54
    bil
    1.31
     trillion
    1.31
    mn
    1.30
    bm
    1.26
     Billion
    1.19
    Activations Density 0.013%

    No Known Activations