© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 12-RES-JB
    11. 4977
    Prev
    Next
    INDEX
    Explanations

    words related to laws and legal matters

    oai_token-act-pair · gpt-3.5-turbo
    Triggered by @bot

    verbs and actions that imply manipulation, change, or significant influence

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 12-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_post
    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_post
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
     mattered
    -0.83
     spelled
    -0.82
     marked
    -0.81
     highlighted
    -0.81
     dashed
    -0.80
     added
    -0.77
     stretched
    -0.77
     cited
    -0.76
     mentioned
    -0.76
     indicated
    -0.76
    POSITIVE LOGITS
    thens
    1.50
    urses
    1.39
    ulates
    1.37
    uces
    1.30
    itates
    1.30
    inates
    1.29
    zes
    1.25
    ates
    1.22
    uates
    1.22
    utes
    1.21
    Activations Density 0.217%

    No Known Activations