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. 17844
    Prev
    Next
    INDEX
    Explanations

    hyperlinks or calls to action in text

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to links and call-to-action prompts

    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
    gling
    -0.58
    usc
    -0.57
     tamp
    -0.57
     Himself
    -0.55
    wered
    -0.55
     AMA
    -0.54
     clim
    -0.52
    course
    -0.52
     capitals
    -0.52
     webpage
    -0.51
    POSITIVE LOGITS
     Oops
    0.74
    idy
    0.68
    oca
    0.63
    ody
    0.62
    common
    0.57
    reshold
    0.55
    Mouse
    0.54
     impunity
    0.53
    Intel
    0.53
    ¬¼
    0.53
    Activations Density 0.042%

    No Known Activations