© 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. 1-RES-JB
    11. 3933
    Prev
    Next
    INDEX
    Explanations

    references to occupations related to the sea, such as sailors and fishermen

    oai_token-act-pair · gpt-3.5-turbo

    references to sailors and fishermen

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    eele
    -0.89
     Beir
    -0.78
    itsch
    -0.76
    osite
    -0.72
    gur
    -0.72
    Spoiler
    -0.70
    à
    -0.70
    erenn
    -0.69
    à¼
    -0.66
    PO
    -0.65
    POSITIVE LOGITS
     sailor
    1.24
     sailors
    1.24
     Sail
    1.07
    boats
    1.03
    boat
    0.97
     sailing
    0.93
     submar
    0.92
     sail
    0.87
     SEAL
    0.85
     fishermen
    0.80
    Activations Density 0.012%

    No Known Activations