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. 6-RES-JB
    6. 15663
    Prev
    Next
    INDEX
    Explanations

    mentions of countries or political entities

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of "Republic."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    TERN
    -0.79
    ãĤ¤
    -0.75
    balls
    -0.71
    Oracle
    -0.68
    berger
    -0.67
    NING
    -0.64
    cial
    -0.64
     needles
    -0.63
    igree
    -0.63
    Ir
    -0.62
    POSITIVE LOGITS
     Republic
    1.07
    oslov
    0.99
    rats
    0.98
    Republic
    0.97
     republic
    0.96
    naire
    0.89
    ans
    0.83
    aine
    0.78
    ation
    0.78
     Seym
    0.77
    Activations Density 0.028%

    No Known Activations