Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 1-RES-JB
    6. 17709
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to a location or person named Monte

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the name "Monte"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Marginal
    -0.74
    inning
    -0.73
    ¿
    -0.73
    oppable
    -0.72
    OTT
    -0.71
    hip
    -0.71
    irlf
    -0.70
    ivities
    -0.70
    hips
    -0.68
    Kate
    -0.68
    POSITIVE LOGITS
     Monte
    1.18
     Carlo
    0.94
    folios
    0.91
    ucci
    0.84
    bris
    0.80
     mosqu
    0.76
    quist
    0.75
    folio
    0.75
    fort
    0.74
    erey
    0.73
    Activations Density 0.006%

    No Known Activations