© 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. 1-RES-JB
    11. 10327
    Prev
    Next
    INDEX
    Explanations

    numeric values indicating quantity or volume

    oai_token-act-pair · gpt-3.5-turbo

    phrases that specify quantities or amounts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     patio
    -0.64
     spectator
    -0.64
    inelli
    -0.64
     Sentinel
    -0.62
     Mirage
    -0.61
     Frontier
    -0.61
     Triangle
    -0.60
    Interstitial
    -0.60
     por
    -0.60
     Valhalla
    -0.60
    POSITIVE LOGITS
     amounts
    1.19
     amount
    1.13
    icult
    0.91
    amount
    0.87
    imei
    0.86
     quantities
    0.85
     quantity
    0.85
    math
    0.84
    entially
    0.80
    iculty
    0.78
    Activations Density 0.013%

    No Known Activations