© 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. 13762
    Prev
    Next
    INDEX
    Explanations

    words related to adventurous activities

    oai_token-act-pair · gpt-3.5-turbo

    references to adventure or adventurous activities

    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
    creen
    -0.76
    itionally
    -0.71
    hovah
    -0.70
     antioxid
    -0.68
    iple
    -0.67
    ounced
    -0.65
    ector
    -0.65
    ombo
    -0.65
    enser
    -0.65
     actu
    -0.64
    POSITIVE LOGITS
    rs
    1.02
     awaits
    0.93
    nels
    0.85
    cean
    0.79
     seekers
    0.78
     Adventure
    0.76
    yrinth
    0.74
     Trave
    0.74
    Adventure
    0.74
     adventurer
    0.72
    Activations Density 0.054%

    No Known Activations