Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 11-RES-JB
    6. 3259
    Prev
    Next
    INDEX
    Explanations

    actions related to physical movement, such as being dragged or escorted

    oai_token-act-pair · gpt-3.5-turbo

    actions related to physical restraint or removal

    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
     Recomm
    -0.64
    acts
    -0.64
     Effective
    -0.63
     Siber
    -0.62
     collaboration
    -0.62
     collaborations
    -0.62
    ITNESS
    -0.60
     pact
    -0.58
     Inher
    -0.58
    asio
    -0.58
    POSITIVE LOGITS
     away
    1.26
     aside
    1.04
     overboard
    0.98
     awa
    0.95
     ashore
    0.94
     onto
    0.90
    away
    0.90
     unconscious
    0.88
     aback
    0.87
     upstairs
    0.87
    Activations Density 0.123%

    No Known Activations