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

    Neuronpedia

    Jacobian LensNEW
    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. 5769
    Prev
    Next
    INDEX
    Explanations

    It looks for phrases related to exploration or discovery, specifically involving nature, animals, and travel

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "to," indicating purpose or intention

    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
     Harmon
    -0.77
     ABV
    -0.75
    Rust
    -0.73
     hemp
    -0.72
    orf
    -0.72
    bass
    -0.71
    rab
    -0.70
    onson
    -0.69
     postage
    -0.68
    ord
    -0.67
    POSITIVE LOGITS
     SEE
    1.46
     VIEW
    1.41
    view
    1.41
     view
    1.40
     viewing
    1.39
     View
    1.34
     viewer
    1.33
     watch
    1.33
     WATCH
    1.33
    View
    1.29
    Activations Density 0.257%

    No Known Activations