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. 9-RES-JB
    6. 7989
    Prev
    Next
    INDEX
    Explanations

    terms related to political and social issues, including references to specific entities such as settlements, territory, IBM, guidance, Facebook, trial, market, EU, etc

    oai_token-act-pair · gpt-3.5-turbo

    keywords related to political, economic, and social issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    '?
    -0.66
    !:
    -0.65
    raq
    -0.62
    essen
    -0.60
    ':
    -0.59
     Bellev
    -0.59
    andom
    -0.59
     pilgr
    -0.58
     Invention
    -0.58
     spokeswoman
    -0.58
    POSITIVE LOGITS
     violates
    1.01
     outweigh
    0.99
     would
    0.97
     constitutes
    0.95
    might
    0.94
    would
    0.93
     might
    0.92
     could
    0.90
    could
    0.89
     wouldn
    0.85
    Activations Density 0.485%

    No Known Activations