© 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. 12-RES-JB
    11. 2723
    Prev
    Next
    INDEX
    Explanations

    phrases indicating contrasts or opposites

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    instances of the word "opposite" and related terminology suggesting contrast or contradiction

    oai_token-act-pair · gpt-4o-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
    adows
    -0.71
    illed
    -0.69
    lov
    -0.69
     Mush
    -0.68
    ushima
    -0.67
     Beans
    -0.66
    uzz
    -0.66
    hens
    -0.66
    uble
    -0.66
    gins
    -0.64
    POSITIVE LOGITS
     sexes
    0.93
     direction
    0.92
     sex
    0.89
     extremes
    0.84
     conclusion
    0.81
     tendency
    0.78
     poles
    0.75
     impression
    0.75
     effect
    0.75
     extreme
    0.74
    Activations Density 0.065%

    No Known Activations