© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 8-RES-JB
    11. 2578
    Prev
    Next
    INDEX
    Explanations

    locations or areas related to bodies of water

    oai_token-act-pair · gpt-3.5-turbo

    references to the Gulf region, particularly the Gulf of Mexico

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Notting
    -0.70
    ATURE
    -0.69
    theless
    -0.66
    lihood
    -0.64
     TYPE
    -0.64
    IBLE
    -0.63
    nings
    -0.63
    keley
    -0.62
    Reply
    -0.62
    ABLE
    -0.61
    POSITIVE LOGITS
     Cooperation
    1.05
    stream
    1.03
     Coast
    1.02
     Islands
    0.87
    front
    0.85
     Stream
    0.79
     monarch
    0.78
     Region
    0.76
     coasts
    0.75
    wash
    0.74
    Activations Density 0.019%

    No Known Activations