© 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 EvalsExportsAPI 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. 6-RES-JB
    11. 8015
    Prev
    Next
    INDEX
    Explanations

    names of individuals or entities, particularly in the context of sports or announcements

    oai_token-act-pair · gpt-3.5-turbo

    names of players or athletes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ictionary
    -0.71
     guiActiveUnfocused
    -0.71
     capitalism
    -0.69
     cartoons
    -0.68
     Recipes
    -0.68
     advertisements
    -0.68
     resolutions
    -0.66
     markup
    -0.64
     censorship
    -0.64
    Internet
    -0.63
    POSITIVE LOGITS
     Jr
    1.02
    Jr
    0.93
     coached
    0.88
     rookie
    0.85
    NBA
    0.84
     teammate
    0.83
    cussion
    0.83
     QB
    0.80
     Sr
    0.80
    tein
    0.77
    Activations Density 0.234%

    No Known Activations