© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 0-RES-JB
    11. 20110
    Prev
    Next
    INDEX
    Explanations

    mentions of specific two-letter sequences, perhaps representing acronyms or codes

    oai_token-act-pair · gpt-3.5-turbo

    the word "be" in various forms and contexts

    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
     Mort
    -0.71
    opol
    -0.68
     impuls
    -0.66
     junior
    -0.65
     slick
    -0.65
     Hom
    -0.65
     mort
    -0.64
     partisans
    -0.62
     reflex
    -0.61
     expense
    -0.61
    POSITIVE LOGITS
    BE
    4.27
    BA
    1.52
    BR
    1.52
    be
    1.48
     BE
    1.48
    BER
    1.42
    BRE
    1.39
    Bey
    1.38
    DE
    1.35
    BI
    1.35
    Activations Density 0.015%

    No Known Activations