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. 0-RES-JB
    6. 2962
    Prev
    Next
    INDEX
    Explanations

    words or abbreviations related to the U.S. state of Massachusetts

    oai_token-act-pair · gpt-3.5-turbo

    references to the state of Massachusetts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Slot
    -0.82
    pec
    -0.72
     Cowboys
    -0.71
    oppable
    -0.66
    ð
    -0.66
    ancies
    -0.64
    iffin
    -0.64
    Cart
    -0.64
    cott
    -0.63
     Canter
    -0.62
    POSITIVE LOGITS
     MA
    3.65
     BA
    1.67
    MA
    1.66
     RI
    1.64
     ME
    1.49
     RA
    1.39
     MD
    1.34
     MO
    1.32
     GA
    1.32
     MPH
    1.31
    Activations Density 0.010%

    No Known Activations