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. 14523
    Prev
    Next
    INDEX
    Explanations

    mentions of a specific technology or product name like "ECCC" or "AMD EPYC."

    oai_token-act-pair · gpt-3.5-turbo

    abbreviations or acronyms related to organizations or products

    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
    dri
    -0.68
    feed
    -0.65
    dust
    -0.64
    ooming
    -0.63
     fond
    -0.61
     sued
    -0.61
     Arbit
    -0.61
     rode
    -0.61
    dos
    -0.59
    amer
    -0.59
    POSITIVE LOGITS
    CCC
    2.93
    YC
    2.11
    JC
    1.51
    YA
    1.46
    YP
    1.37
    KK
    1.34
    escent
    1.32
    JD
    1.21
    ISE
    1.20
     Penguin
    1.11
    Activations Density 0.078%

    No Known Activations