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. 3-RES-JB
    6. 10189
    Prev
    Next
    INDEX
    Explanations

    proper names or terms related to different countries and individuals

    oai_token-act-pair · gpt-3.5-turbo

    linguistic characters or symbols, particularly unusual or diacritically marked letters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    IPS
    -0.70
    imer
    -0.70
    icles
    -0.68
    icle
    -0.66
    andel
    -0.65
    asket
    -0.63
    ochemical
    -0.63
    =-=-=-=-
    -0.62
    iffs
    -0.62
    quart
    -0.62
    POSITIVE LOGITS
    cus
    0.85
    ternity
    0.80
    lisher
    0.75
    ð
    0.73
    mented
    0.72
    lette
    0.72
    cci
    0.69
    lio
    0.68
    pees
    0.68
    enced
    0.67
    Activations Density 0.008%

    No Known Activations