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. 12-RES-JB
    6. 15091
    Prev
    Next
    INDEX
    Explanations

    phrases related to accomplishment or success

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    references to notable individuals or entities and their achievements or impact

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 12-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_post
    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_post
    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
    ebin
    -0.65
    anian
    -0.59
    wik
    -0.58
    DonaldTrump
    -0.56
    izo
    -0.56
     facult
    -0.56
    Wik
    -0.54
    fortunately
    -0.53
    retty
    -0.53
    Ô
    -0.52
    POSITIVE LOGITS
     onstage
    0.60
     perish
    0.55
     throats
    0.52
     compete
    0.49
     totaled
    0.49
     slaughtered
    0.48
     dies
    0.48
     perished
    0.47
     starve
    0.47
     rack
    0.47
    Activations Density 0.979%

    No Known Activations