© 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. 11-RES-JB
    11. 7513
    Prev
    Next
    INDEX
    Explanations

    phrases related to tying or binding objects together

    oai_token-act-pair · gpt-3.5-turbo

    references to injury or harm involving physical objects or 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
     Booker
    -0.79
    audi
    -0.79
     Miller
    -0.74
    geist
    -0.74
    Miller
    -0.73
    izu
    -0.73
    htaking
    -0.72
     Atmosp
    -0.70
     Pepsi
    -0.69
     Salam
    -0.69
    POSITIVE LOGITS
     knots
    1.93
     ropes
    1.92
     rope
    1.91
     knot
    1.87
     cords
    1.74
     tether
    1.50
     straps
    1.49
     Knot
    1.46
     nylon
    1.40
     leash
    1.39
    Activations Density 0.315%

    No Known Activations