© 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. 10746
    Prev
    Next
    INDEX
    Explanations

    the letter "C" followed by other specific letters in a text

    oai_token-act-pair · gpt-3.5-turbo

    specific letters, symbols, and words that indicate unique identifiers or classifications

    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
     Dise
    -0.91
     Raz
    -0.88
     Dickinson
    -0.83
     dime
    -0.82
     Iz
    -0.81
     Ivy
    -0.79
     Ezra
    -0.79
     Rig
    -0.78
     Dh
    -0.78
     Crane
    -0.78
    POSITIVE LOGITS
     Mun
    0.95
    mun
    0.93
    bil
    0.83
    atur
    0.83
    atalie
    0.80
     Blair
    0.79
    970
    0.78
    ala
    0.77
    ela
    0.76
     Hezbollah
    0.75
    Activations Density 0.457%

    No Known Activations