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. 14625
    Prev
    Next
    INDEX
    Explanations

    technological terms and references related to computer hardware and software

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

    references to popular video games and their characters

    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
     Cosponsors
    -0.75
     improvised
    -0.62
     wig
    -0.60
     conson
    -0.60
     duly
    -0.59
     aperture
    -0.58
     transcript
    -0.58
     reciproc
    -0.58
    */(
    -0.58
     fals
    -0.57
    POSITIVE LOGITS
     Simulator
    1.15
     Tycoon
    1.07
     Clicker
    1.05
     Ops
    1.02
     Empires
    1.00
     Souls
    1.00
     Pinball
    0.99
    Cry
    0.98
     Rampage
    0.97
     Kingdoms
    0.96
    Activations Density 0.222%

    No Known Activations