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. 10-RES-JB
    6. 3997
    Prev
    Next
    INDEX
    Explanations

    superlatives such as "most," "best," and "safest."

    oai_token-act-pair · gpt-3.5-turbo

    superlative adjectives and phrases indicating extremes or best/worst rankings

    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
    aucuses
    -0.84
    rils
    -0.84
    ãĤ¦ãĤ¹
    -0.83
    appings
    -0.82
     Cosponsors
    -0.80
    é¾į
    -0.79
    ravings
    -0.79
    IGHTS
    -0.78
    Ô
    -0.75
    rahim
    -0.74
    POSITIVE LOGITS
     thing
    1.00
     ever
    0.93
     imaginable
    0.92
     bidder
    0.91
     piece
    0.90
     conceivable
    0.90
     foreigner
    0.87
     performer
    0.86
     applicant
    0.85
     single
    0.85
    Activations Density 0.136%

    No Known Activations