© 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. 11961
    Prev
    Next
    INDEX
    Explanations

    words related to conflict, activism, and social or political struggles

    oai_token-act-pair · gpt-3.5-turbo

    terms related to struggles and conflicts against various issues

    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
     waivers
    -0.71
     Mist
    -0.63
     Investigator
    -0.62
     inspected
    -0.58
     unpop
    -0.58
    ij士
    -0.57
     Seym
    -0.57
     certific
    -0.57
     Constable
    -0.56
     Availability
    -0.56
    POSITIVE LOGITS
     against
    1.25
     waged
    1.16
    against
    1.12
     Against
    1.10
    back
    0.88
     raging
    0.85
     for
    0.81
    front
    0.81
     between
    0.80
    Against
    0.80
    Activations Density 0.118%

    No Known Activations