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. 8-RES-JB
    6. 23939
    Prev
    Next
    INDEX
    Explanations

    mentions or references to friends or allies

    oai_token-act-pair · gpt-3.5-turbo

    references to friends and social connections

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    appropriately
    -0.78
    pleting
    -0.70
    apers
    -0.67
    ival
    -0.66
    itized
    -0.66
    eway
    -0.66
    clusive
    -0.65
    sole
    -0.64
    imon
    -0.64
     lasting
    -0.62
    POSITIVE LOGITS
     Adam
    0.71
     Robb
    0.70
    liest
    0.67
     Brigham
    0.66
     Jonah
    0.66
     Franks
    0.66
     Gabriel
    0.65
     Cous
    0.65
    liness
    0.64
     Nath
    0.64
    Activations Density 0.071%

    No Known Activations