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. 9-RES-JB
    6. 14977
    Prev
    Next
    INDEX
    Explanations

    mentions of actions that can be done without specific resources or efforts

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating the absence of effort or difficulty in achieving a task

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    soType
    -1.10
     Facts
    -0.85
    realDonaldTrump
    -0.81
    facts
    -0.74
    ciation
    -0.72
    isSpecialOrderable
    -0.70
     Advoc
    -0.69
     Excellence
    -0.68
    Values
    -0.66
    geist
    -0.66
    POSITIVE LOGITS
     hassle
    1.26
     cumbersome
    1.19
     pesky
    1.14
     clutter
    1.14
     worrying
    1.11
     needing
    1.11
     cumbers
    1.10
     bulky
    1.08
     worry
    1.07
     costly
    1.02
    Activations Density 0.397%

    No Known Activations