© 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. 10-RES-JB
    11. 3198
    Prev
    Next
    INDEX
    Explanations

    locations or places such as hospitals, hotels, airports, and clinics

    oai_token-act-pair · gpt-3.5-turbo

    references to places commonly associated with services, particularly healthcare and hospitality

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Marketable
    -0.88
    iggurat
    -0.66
     Leilan
    -0.66
     Slightly
    -0.65
     onstage
    -0.65
     supra
    -0.65
     Cathedral
    -0.64
     LLP
    -0.63
    fecture
    -0.63
    insula
    -0.62
    POSITIVE LOGITS
     closures
    1.15
    goers
    1.06
     visits
    0.99
    going
    0.97
     dwell
    0.91
     owners
    0.90
    owners
    0.89
     operators
    0.89
     clos
    0.88
     hopping
    0.87
    Activations Density 0.258%

    No Known Activations