© 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. 2-RES-JB
    11. 17569
    Prev
    Next
    INDEX
    Explanations

    specific symbols used for technical instructions

    oai_token-act-pair · gpt-3.5-turbo

    indicators or symbols that reference menus or options in a user interface

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    iqueness
    -1.01
     destro
    -0.98
    onial
    -0.85
    etheless
    -0.83
    acies
    -0.81
    onite
    -0.79
    teenth
    -0.77
    yssey
    -0.77
    erville
    -0.77
    mares
    -0.75
    POSITIVE LOGITS
    _>
    1.40
     >
    0.94
    .<
    0.84
    =>
    0.83
    -->
    0.83
    NOR
    0.81
     (<
    0.77
     <!--
    0.77
    âĸĴ
    0.77
    ALS
    0.76
    Activations Density 0.011%

    No Known Activations