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. 8019
    Prev
    Next
    INDEX
    Explanations

    phrases that include the word "with"

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate levels of certainty or conformance

    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
    estate
    -0.72
    eworks
    -0.69
    ksh
    -0.68
    IA
    -0.67
     Related
    -0.66
    soon
    -0.63
    BN
    -0.63
    etary
    -0.62
    CB
    -0.61
     Introdu
    -0.60
    POSITIVE LOGITS
     impunity
    1.30
     utmost
    1.29
     dignity
    1.24
     gust
    1.18
     vig
    1.16
     ease
    1.14
     certainty
    1.13
     abandon
    1.11
     reverence
    1.11
     confidence
    1.11
    Activations Density 0.136%

    No Known Activations