© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 16574
    Prev
    Next
    INDEX
    Explanations

    possessive constructions, especially focusing on relationships between people

    oai_token-act-pair · gpt-3.5-turbo

    keywords and phrases associated with personal experiences or opinions

    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
     of
    -0.92
    of
    -0.79
     thereof
    -0.78
     Of
    -0.75
    oft
    -0.74
    Of
    -0.73
     OF
    -0.67
    OF
    -0.50
     portfolios
    -0.46
    ta
    -0.46
    POSITIVE LOGITS
    farious
    0.58
    estern
    0.57
    versible
    0.54
    StreamerBot
    0.52
    ActionCode
    0.52
    isSpecial
    0.52
    anyon
    0.49
    igenous
    0.49
    actus
    0.49
    EMP
    0.49
    Activations Density 1.317%

    No Known Activations