© 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. 8-RES-JB
    11. 1008
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal or political discussions

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to legal and regulatory matters

    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
     Whilst
    -0.67
     whilst
    -0.65
    Firstly
    -0.64
    âĢ¦]
    -0.60
    ³³
    -0.58
    ↵Âł
    -0.57
    Contents
    -0.57
    ³³³³
    -0.56
    âĢ¦)
    -0.56
    Âł
    -0.56
    POSITIVE LOGITS
     Buffett
    0.71
     Canaver
    0.64
     Bezos
    0.58
     Gorsuch
    0.57
     Musk
    0.56
     Southwest
    0.56
     Cohn
    0.55
     Pruitt
    0.54
     DeVos
    0.54
     Harbaugh
    0.53
    Activations Density 3.612%

    No Known Activations