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. 1-RES-JB
    6. 12717
    Prev
    Next
    INDEX
    Explanations

    acronyms related to various technical terms, especially "SAN" (Storage Area Network)

    oai_token-act-pair · gpt-3.5-turbo

    the abbreviation "SAN" and its context related to places or entities

    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
    unct
    -0.66
     pupils
    -0.62
     Wheel
    -0.61
     crank
    -0.61
    onom
    -0.61
     Awakening
    -0.60
     Thr
    -0.60
    aed
    -0.60
    ï¸ı
    -0.59
     Siren
    -0.59
    POSITIVE LOGITS
    SAN
    1.52
     SAN
    1.22
    AMI
    1.04
    San
    0.96
    DAQ
    0.96
     ANGEL
    0.94
    ctuary
    0.93
    MAR
    0.92
    IFIC
    0.89
    BIL
    0.89
    Activations Density 0.006%

    No Known Activations