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. 4-RES-JB
    6. 15056
    Prev
    Next
    INDEX
    Explanations

    locations or entities containing the word "Fremont"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the location Frem (Fremont)

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

    No Comments

    Negative Logits
     Cassidy
    -0.77
    lihood
    -0.72
    draw
    -0.71
     Izan
    -0.68
     Beg
    -0.68
     Mehran
    -0.64
     Gerry
    -0.63
     Paige
    -0.63
    lift
    -0.63
    ++++++++++++++++
    -0.62
    POSITIVE LOGITS
    antle
    1.43
     Frem
    0.90
    actory
    0.89
    ilit
    0.88
    asonry
    0.86
    puter
    0.85
    cipled
    0.83
    ont
    0.83
    ersen
    0.81
    shire
    0.81
    Activations Density 0.012%

    No Known Activations