© 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. 20513
    Prev
    Next
    INDEX
    Explanations

    keywords related to various concepts such as holidays, behaviors, substances, and medical conditions

    oai_token-act-pair · gpt-3.5-turbo

    terms related to significant societal issues and classifications

    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
     Lumpur
    -0.75
    tnc
    -0.70
    usalem
    -0.68
    doms
    -0.65
     renovations
    -0.65
    racuse
    -0.64
    asonic
    -0.63
    anooga
    -0.63
    azeera
    -0.63
    ModLoader
    -0.63
    POSITIVE LOGITS
     invented
    1.02
     characterized
    0.98
     synonymous
    0.95
     whose
    0.94
     affecting
    0.94
     deserving
    0.94
     requiring
    0.92
     prized
    0.91
     consisting
    0.91
     favored
    0.90
    Activations Density 0.256%

    No Known Activations