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. 11-RES-JB
    6. 19951
    Prev
    Next
    INDEX
    Explanations

    country names

    oai_token-act-pair · gpt-3.5-turbo

    references to specific countries and geopolitical issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    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
    lance
    -0.77
    lesi
    -0.67
    ppings
    -0.66
    mons
    -0.66
    DonaldTrump
    -0.65
    laws
    -0.64
    ateurs
    -0.64
    netflix
    -0.64
    BILITIES
    -0.62
    cd
    -0.62
    POSITIVE LOGITS
     ratio
    1.37
     Ratio
    1.28
     hybrids
    1.24
     hybrid
    1.23
     combo
    1.23
     dich
    1.20
     relationship
    1.19
     partnership
    1.17
     rivalry
    1.17
     ratios
    1.16
    Activations Density 0.201%

    No Known Activations