© 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. 10178
    Prev
    Next
    INDEX
    Explanations

    locations and street intersections

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "and" in the text

    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
    >[
    -0.87
    role
    -0.75
    ubi
    -0.75
    oru
    -0.73
    BIP
    -0.73
    rared
    -0.73
    ombo
    -0.72
    udeb
    -0.72
    rats
    -0.72
    icc
    -0.72
    POSITIVE LOGITS
     Canal
    1.23
     Broadway
    1.21
     Boulevard
    1.20
     Fulton
    1.17
     Avenue
    1.13
     Lexington
    1.13
     Sunset
    1.12
     Vine
    1.11
     Market
    1.08
     Riverside
    1.07
    Activations Density 0.061%

    No Known Activations