© 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. 8-RES-JB
    11. 7756
    Prev
    Next
    INDEX
    Explanations

    special characters and symbols

    oai_token-act-pair · gpt-3.5-turbo

    patterns or symbols that indicate formatting or structure in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    inav
    -0.72
    lling
    -0.71
    ollar
    -0.69
    irst
    -0.66
     spir
    -0.65
     clipping
    -0.64
     deliber
    -0.61
    lections
    -0.60
    ovo
    -0.60
    pora
    -0.59
    POSITIVE LOGITS
    */
    1.02
    *****
    0.89
     =================================================================
    0.87
    ===
    0.84
    =-=-
    0.84
    -->
    0.83
    =-
    0.76
    ---
    0.76
    edit
    0.76
    quote
    0.76
    Activations Density 0.065%

    No Known Activations