© 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. 6-RES-JB
    11. 9321
    Prev
    Next
    INDEX
    Explanations

    phrases related to political unrest or international conflicts

    oai_token-act-pair · gpt-3.5-turbo

    the word "some" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ocene
    -0.77
    tainment
    -0.67
    istan
    -0.63
    uckle
    -0.63
    gon
    -0.62
    ée
    -0.62
    livion
    -0.60
    ared
    -0.59
     Forever
    -0.58
    ean
    -0.57
    POSITIVE LOGITS
    ones
    0.93
    body
    0.93
     semblance
    0.90
    place
    0.89
    how
    0.89
     unspecified
    0.81
     notable
    0.75
     dozen
    0.73
     mornings
    0.72
     provinces
    0.70
    Activations Density 0.116%

    No Known Activations