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. 278
    Prev
    Next
    INDEX
    Explanations

    phrases related to online sharing or publication

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating inclusion or references to external sources

    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
    tis
    -0.90
    ecast
    -0.84
    meric
    -0.80
    chool
    -0.78
    uel
    -0.75
    riger
    -0.74
     Flavoring
    -0.70
    ertain
    -0.70
    esters
    -0.70
    dom
    -0.69
    POSITIVE LOGITS
     references
    1.24
     quotes
    1.22
     phrases
    1.17
     descriptions
    1.13
     excerpts
    1.13
     slogans
    1.10
     statements
    1.09
     wording
    1.08
     disclaimer
    1.07
     disclaim
    1.07
    Activations Density 0.375%

    No Known Activations