© 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 EvalsExportsinterp-engineNEWAPI 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. 20350
    Prev
    Next
    INDEX
    Explanations

    content related to pleading or requesting strongly

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "beg" and its variations

    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
     Cheong
    -0.78
    azeera
    -0.67
    iership
    -0.66
    ulty
    -0.66
    jiang
    -0.66
    productive
    -0.65
     Democr
    -0.62
    idents
    -0.62
    cyclop
    -0.61
    uclear
    -0.61
    POSITIVE LOGITS
     forgiveness
    1.17
     pardon
    1.08
    otten
    0.92
     begging
    0.83
     patience
    0.80
    FontSize
    0.80
    ingly
    0.75
     mercy
    0.75
    ModLoader
    0.72
     redemption
    0.71
    Activations Density 0.072%

    No Known Activations