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. 2-RES-JB
    6. 18156
    Prev
    Next
    INDEX
    Explanations

    currency symbols

    oai_token-act-pair · gpt-3.5-turbo

    special characters and symbols, particularly in the context of formatting or encoding

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    hattan
    -0.70
     Widow
    -0.68
    wagen
    -0.68
     Moody
    -0.66
     Bethesda
    -0.65
     Mond
    -0.65
     Crusher
    -0.65
     Tid
    -0.62
     Ces
    -0.61
     Tec
    -0.60
    POSITIVE LOGITS
    â
    1.16
    ĵ
    1.16
    Ĥ
    1.12
    Ħ¢
    1.12
    ¥ŀ
    1.11
    ł
    1.04
    Ħ
    1.03
    Ĥª
    1.02
    ĥ
    1.00
    Ļ
    0.99
    Activations Density 0.003%

    No Known Activations