© 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. 11-RES-JB
    11. 4914
    Prev
    Next
    INDEX
    Explanations

    number-related information, such as percentages, quantities, and statistics

    oai_token-act-pair · gpt-3.5-turbo

    mentions of statistics or numerical data related to the United States

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ortunately
    -0.94
    Þ
    -0.92
    isSpecial
    -0.88
    ò
    -0.87
     exting
    -0.87
    aditional
    -0.87
     pione
    -0.87
    ß
    -0.85
    Ý
    -0.85
     practition
    -0.84
    POSITIVE LOGITS
    7601
    0.44
    SpaceEngineers
    0.43
    rigan
    0.43
    Detailed
    0.43
    frey
    0.43
    ighthouse
    0.42
    Pg
    0.40
    mma
    0.40
    GV
    0.40
    ulet
    0.39
    Activations Density 0.406%

    No Known Activations