© 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. 11-RES-JB
    11. 20963
    Prev
    Next
    INDEX
    Explanations

    phrases related to political speeches and actions

    oai_token-act-pair · gpt-3.5-turbo

    statements related to political events and figures

    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
    !'
    -0.61
     sqor
    -0.58
    ß
    -0.53
    âĢIJ
    -0.52
    Þ
    -0.48
    æĸ¹
    -0.48
    ãĢį
    -0.48
     withd
    -0.48
    rawdownloadcloneembedreportprint
    -0.47
    LT
    -0.47
    POSITIVE LOGITS
     "'
    1.76
     "
    1.71
     "[
    1.63
     "âĢ¦
    1.57
     "...
    1.55
     "(
    1.39
     ''
    1.37
     "#
    1.28
     ".
    1.26
     "$
    1.20
    Activations Density 1.513%

    No Known Activations