© 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. 13184
    Prev
    Next
    INDEX
    Explanations

    instances where things are being affected or considered

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to significant events or changes affecting cities or communities

    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
    vernment
    -0.70
    ocity
    -0.64
     livest
    -0.63
    Publisher
    -0.59
     truth
    -0.59
     VERS
    -0.59
     equivalent
    -0.58
    acity
    -0.58
    UTH
    -0.57
     Period
    -0.57
    POSITIVE LOGITS
     impacted
    1.24
     affected
    1.22
     singled
    1.10
     targets
    1.08
     targeted
    1.03
     eyed
    0.96
     excluded
    0.96
     mentioned
    0.95
    affected
    0.94
     highlighted
    0.92
    Activations Density 0.461%

    No Known Activations