© 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 EvalsExportsinterp-engineNEWAPI 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. 11-RES-JB
    11. 2823
    Prev
    Next
    INDEX
    Explanations

    instructions related to adventure activities

    oai_token-act-pair · gpt-3.5-turbo

    content related to dramatic or dangerous situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    resent
    -0.85
    soType
    -0.82
     Innocent
    -0.77
     Votes
    -0.75
     Cosponsors
    -0.75
     Consumers
    -0.74
    present
    -0.74
    esson
    -0.73
     Lerner
    -0.73
    Address
    -0.71
    POSITIVE LOGITS
     parachute
    1.71
     glide
    1.70
     parach
    1.62
     rapp
    1.56
     leaping
    1.54
     jumping
    1.52
     jump
    1.50
     takeoff
    1.49
     hover
    1.47
     landing
    1.46
    Activations Density 0.486%

    No Known Activations