Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 8578
    Prev
    Next
    INDEX
    Explanations

    a call to action related to responding to an article or opinion piece

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to submitting opinions or letters to an editor

    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
    asus
    -0.66
    gow
    -0.66
    gr
    -0.62
     Goddess
    -0.59
    runs
    -0.57
     SOLD
    -0.57
    ------------------------------------------------
    -0.56
    gins
    -0.54
    arius
    -0.53
    riages
    -0.53
    POSITIVE LOGITS
    iquette
    0.72
     Cecil
    0.64
    tips
    0.64
     Comment
    0.63
     substantive
    0.63
    Comment
    0.62
    comment
    0.62
    utenberg
    0.61
     Login
    0.61
     corrections
    0.60
    Activations Density 0.102%

    No Known Activations