© 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. 10-RES-JB
    11. 12431
    Prev
    Next
    INDEX
    Explanations

    terms related to expenses or financial matters

    oai_token-act-pair · gpt-3.5-turbo

    various forms of the word "expand" and its related derivatives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ball
    -0.72
    balls
    -0.70
    âĸ¬âĸ¬
    -0.66
     Carnival
    -0.65
    BOOK
    -0.63
    sonian
    -0.62
    footed
    -0.61
    âĸ¬
    -0.61
    BALL
    -0.60
     striking
    -0.60
    POSITIVE LOGITS
    ansion
    1.63
    onential
    1.54
    anding
    1.48
    onent
    1.45
    anded
    1.44
    osed
    1.39
    ulsion
    1.36
    ensive
    1.34
    ressed
    1.30
    ressive
    1.29
    Activations Density 0.015%

    No Known Activations