© 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. 10-RES-JB
    11. 11575
    Prev
    Next
    INDEX
    Explanations

    capital letters at the beginning of a word or abbreviation

    oai_token-act-pair · gpt-3.5-turbo

    single-letter or short acronyms and their significance in the context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     pony
    -0.72
     FIRST
    -0.67
    ãĢı
    -0.65
     SUPER
    -0.64
     Hobbit
    -0.64
    Ħ¢
    -0.63
     PATH
    -0.63
     Incarnation
    -0.63
     LEGO
    -0.63
     WAY
    -0.62
    POSITIVE LOGITS
    ocally
    1.29
    ately
    1.20
    sequently
    1.20
    ifully
    1.18
    rarily
    1.18
    ogether
    1.17
    pecially
    1.16
    itionally
    1.16
    cially
    1.13
    beit
    1.13
    Activations Density 0.257%

    No Known Activations