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. 1991
    Prev
    Next
    INDEX
    Explanations

    phrases suggesting doubt or uncertainty

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating uncertainty or skepticism about future events

    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
    ngth
    -0.73
    raq
    -0.68
    alde
    -0.67
    verbs
    -0.65
     speculated
    -0.65
    ription
    -0.64
    clamation
    -0.62
    aina
    -0.61
     reminds
    -0.60
    culated
    -0.60
    POSITIVE LOGITS
     anytime
    1.46
     anymore
    1.34
     ever
    1.19
     anything
    1.16
     EVER
    1.15
     anywhere
    1.11
     any
    1.10
    ever
    1.00
     nor
    0.99
     whatsoever
    0.96
    Activations Density 0.353%

    No Known Activations