© 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. 19363
    Prev
    Next
    INDEX
    Explanations

    proper nouns or phrases related to geographic locations

    oai_token-act-pair · gpt-3.5-turbo

    punctuation or sentence-ending markers

    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
     allowance
    -0.83
     clinch
    -0.72
     cabbage
    -0.69
     idle
    -0.68
    unts
    -0.67
     gust
    -0.67
     affili
    -0.67
    ascus
    -0.66
    idth
    -0.66
     confir
    -0.65
    POSITIVE LOGITS
     Essentially
    1.15
     Specifically
    1.14
     Located
    1.14
     Apparently
    1.08
     Initially
    1.07
     Featuring
    1.05
     Though
    1.05
     Previously
    1.04
     Basically
    1.04
     According
    1.03
    Activations Density 0.466%

    No Known Activations