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. 11-RES-JB
    6. 17023
    Prev
    Next
    INDEX
    Explanations

    phrases indicating certainty or likelihood

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating certainty or confidence in information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Reviewer
    -0.81
    ructose
    -0.77
    */(
    -0.72
    quished
    -0.70
    Interstitial
    -0.69
    rients
    -0.69
     Companion
    -0.68
    Beh
    -0.63
    lang
    -0.63
    xual
    -0.61
    POSITIVE LOGITS
     certainty
    1.67
     guarantee
    1.25
     probable
    1.25
     probability
    1.25
     likelihood
    1.14
    certain
    1.14
     assurance
    1.13
     assured
    1.13
     confident
    1.13
     certain
    1.13
    Activations Density 0.648%

    No Known Activations