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. 6-RES-JB
    6. 8319
    Prev
    Next
    INDEX
    Explanations

    instances where individuals are physically confined or immobilized

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "trapped" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    issance
    -0.92
    sych
    -0.92
    sburgh
    -0.75
    itage
    -0.74
    roxy
    -0.72
    ific
    -0.69
    resso
    -0.68
    eds
    -0.66
    nings
    -0.65
    frey
    -0.65
    POSITIVE LOGITS
     trapped
    0.81
     souls
    0.78
    DonaldTrump
    0.75
    Quantity
    0.74
    untarily
    0.74
     pigeon
    0.73
    ravel
    0.70
     Labyrinth
    0.69
    ©¶æ¥µ
    0.68
     ducks
    0.68
    Activations Density 0.034%

    No Known Activations