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. 1-RES-JB
    6. 9680
    Prev
    Next
    INDEX
    Explanations

    geographical locations

    oai_token-act-pair · gpt-3.5-turbo

    references to colors and specific items associated with those colors

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ividual
    -0.47
    elvet
    -0.39
    ilet
    -0.39
    ioxide
    -0.38
    iland
    -0.36
    ebted
    -0.35
    Integ
    -0.35
    example
    -0.34
    âĵĺ
    -0.34
    Nazi
    -0.33
    POSITIVE LOGITS
    ĵĺ
    0.50
    terness
    0.47
    NetMessage
    0.42
     Morty
    0.40
    Ĥª
    0.38
    ©¶æ¥µ
    0.38
     artif
    0.37
     ãĢĮ
    0.37
     pse
    0.36
    wcs
    0.35
    Activations Density 11.430%

    No Known Activations