© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 9-RES-JB
    6. 22882
    Prev
    Next
    INDEX
    Explanations

    words or phrases associated with financial transactions

    oai_token-act-pair · gpt-3.5-turbo

    various forms of emphasis or strong opinions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     tram
    -0.76
     veter
    -0.76
     swall
    -0.75
     satell
    -0.71
     chimpan
    -0.69
     swallow
    -0.69
     electron
    -0.68
     rye
    -0.68
     mushroom
    -0.68
     playable
    -0.68
    POSITIVE LOGITS
    According
    1.42
    However
    1.36
    While
    1.35
    Others
    1.34
    Among
    1.33
    Meanwhile
    1.31
    Earlier
    1.29
    Despite
    1.29
    Speaking
    1.29
    Although
    1.29
    Activations Density 0.291%

    No Known Activations