© 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. 6-RES-JB
    11. 14519
    Prev
    Next
    INDEX
    Explanations

    names or terms related to astrology

    oai_token-act-pair · gpt-3.5-turbo

    terms related to roles in a specific context, likely focusing on various professional or functional titles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    riad
    -0.78
     Gingrich
    -0.77
    REM
    -0.70
    ELF
    -0.70
    EMP
    -0.70
     EntityItem
    -0.70
    TextColor
    -0.68
    FontSize
    -0.67
    IRE
    -0.65
    LOD
    -0.65
    POSITIVE LOGITS
    ogical
    1.34
    anguage
    1.01
    oola
    1.01
    ateral
    0.96
    lees
    0.94
    ution
    0.94
    ounge
    0.89
    leys
    0.88
    sed
    0.87
    iers
    0.85
    Activations Density 0.027%

    No Known Activations