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. 15380
    Prev
    Next
    INDEX
    Explanations

    phrases related to physical and geographical enclosures or boundaries

    oai_token-act-pair · gpt-3.5-turbo

    the prefix "enc" and variations of it in various contexts

    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
     gestation
    -0.69
     launchers
    -0.63
    wagen
    -0.62
    DAY
    -0.61
     dispens
    -0.61
     concurrent
    -0.61
     Weeks
    -0.59
     cleaner
    -0.59
    WB
    -0.59
     Jama
    -0.58
    POSITIVE LOGITS
    ounters
    1.45
    ourage
    1.35
    oding
    1.32
    rypted
    1.31
    ryption
    1.30
    umbered
    1.28
    oded
    1.27
    ounter
    1.24
    oder
    1.24
    ased
    1.23
    Activations Density 0.023%

    No Known Activations