© 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. 8-RES-JB
    11. 4237
    Prev
    Next
    INDEX
    Explanations

    quantities or numbers

    oai_token-act-pair · gpt-3.5-turbo

    questions or statements that inquire about quantities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    hern
    -0.76
    UAL
    -0.72
    afort
    -0.70
    olitics
    -0.70
    ivism
    -0.67
    Mobil
    -0.66
    etry
    -0.66
    avior
    -0.64
    owder
    -0.64
    aband
    -0.63
    POSITIVE LOGITS
     times
    1.23
     thousand
    0.96
     calories
    0.95
     servings
    0.93
     hundred
    0.91
     instances
    0.88
     copies
    0.88
     hours
    0.87
     people
    0.87
     parentheses
    0.87
    Activations Density 0.045%

    No Known Activations