© 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. 21115
    Prev
    Next
    INDEX
    Explanations

    phrases related to activities done with others

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "with."

    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
    nery
    -0.81
    hood
    -0.75
    iture
    -0.71
    soon
    -0.71
     (.
    -0.70
    itures
    -0.69
    sburg
    -0.68
     unless
    -0.68
     furthermore
    -0.68
    meal
    -0.67
    POSITIVE LOGITS
     impunity
    1.31
    stood
    1.30
     colleagues
    1.01
     regard
    1.00
     regards
    1.00
     him
    0.99
     us
    0.97
     pals
    0.94
     coworkers
    0.92
     them
    0.91
    Activations Density 0.208%

    No Known Activations