© 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. 10-RES-JB
    11. 20317
    Prev
    Next
    INDEX
    Explanations

    references to the word "express" in a technical or transportation context

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "Express" and its variations

    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
     Skydragon
    -0.76
     Shades
    -0.70
     Icar
    -0.67
    fman
    -0.65
    atch
    -0.63
    adding
    -0.63
     Shattered
    -0.61
    =-=-=-=-
    -0.61
     bump
    -0.61
     Rez
    -0.60
    POSITIVE LOGITS
    ions
    1.00
    iveness
    0.97
    ivity
    0.93
    ively
    0.87
    iment
    0.81
    ional
    0.81
    ivities
    0.79
    way
    0.77
    Route
    0.77
    ist
    0.77
    Activations Density 0.050%

    No Known Activations