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

    Neuronpedia

    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. 7-RES-JB
    11. 13936
    Prev
    Next
    INDEX
    Explanations

    mentions of people speaking in news articles

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "said" and variations of it, indicating statements or quotes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ãĥ¼ãĥĨãĤ£
    -0.83
    ãĥİ
    -0.78
    illions
    -0.75
    onut
    -0.75
    respective
    -0.73
    OTAL
    -0.71
    illion
    -0.70
    ãĥ¯
    -0.69
    gradient
    -0.68
    figure
    -0.68
    POSITIVE LOGITS
     bluntly
    0.82
     sarcast
    0.80
     rhet
    0.74
     anecd
    0.71
     forcefully
    0.68
     Cuomo
    0.68
     dismiss
    0.66
     emphatically
    0.66
     confidently
    0.66
     incred
    0.64
    Activations Density 0.166%

    No Known Activations