© 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. 22663
    Prev
    Next
    INDEX
    Explanations

    the word "Marco"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the name "Marco."

    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
    shed
    -0.73
    Bow
    -0.70
    reth
    -0.64
     workplaces
    -0.64
     occup
    -0.63
     [&
    -0.63
    olson
    -0.62
     OU
    -0.62
    HQ
    -0.61
    hod
    -0.61
    POSITIVE LOGITS
     Marco
    3.61
    Marco
    3.08
     Rubio
    2.00
     Jeb
    1.54
     Roberto
    1.33
     Giovanni
    1.30
    Cruz
    1.28
     Rafael
    1.26
     Cruz
    1.26
     Lindsey
    1.25
    Activations Density 0.008%

    No Known Activations