© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 12-RES-JB
    11. 4593
    Prev
    Next
    INDEX
    Explanations

    sports-related topics, specifically involving drafts, interviews, and performances

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    phrases related to competition and performance in sports or entertainment contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 12-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_post
    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_post
    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
    Synopsis
    -0.69
     awaits
    -0.68
     await
    -0.66
    Requires
    -0.63
    theless
    -0.59
     unlikely
    -0.58
     unworthy
    -0.58
     pleasures
    -0.57
    izens
    -0.55
     strives
    -0.55
    POSITIVE LOGITS
     [
    1.16
     ['
    1.09
     ["
    1.01
     stuff
    0.95
     guys
    0.88
     guy
    0.86
     maybe
    0.86
    laughs
    0.84
     kinda
    0.83
    ,"
    0.83
    Activations Density 0.831%

    No Known Activations