© 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. 22930
    Prev
    Next
    INDEX
    Explanations

    mentions of the importance or impact of events or actions

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating positive sentiment or enjoyment

    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
    oulos
    -0.59
     Adin
    -0.54
    bestos
    -0.54
     Kaplan
    -0.50
     Madd
    -0.49
     Sutton
    -0.49
     meanwhile
    -0.49
     postwar
    -0.48
     Whitman
    -0.48
     moreover
    -0.48
    POSITIVE LOGITS
     alot
    0.89
     ;)
    0.73
     haha
    0.69
     :)
    0.67
     crap
    0.67
     shit
    0.66
     dont
    0.65
     :(
    0.64
     pic
    0.64
     gonna
    0.63
    Activations Density 2.133%

    No Known Activations