© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 11605
    Prev
    Next
    INDEX
    Explanations

    cities or locations ending in 'pton'

    oai_token-act-pair · gpt-3.5-turbo

    references to the locations with "pton" in their names

    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
     exped
    -0.75
     hands
    -0.70
     instinct
    -0.68
     dogs
    -0.63
     budgetary
    -0.63
     adop
    -0.63
     orders
    -0.61
     screens
    -0.60
     synchronized
    -0.59
     Grateful
    -0.59
    POSITIVE LOGITS
    pton
    5.00
    pta
    1.56
    pson
    1.32
    pt
    1.29
    nton
    1.18
    xton
    1.15
    berman
    1.14
    enegger
    1.13
    yton
    1.11
    ppa
    1.09
    Activations Density 0.013%

    No Known Activations