© 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. 8-RES-JB
    11. 11440
    Prev
    Next
    INDEX
    Explanations

    the word "opposite" in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    concepts of opposition or contradiction

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    uay
    -0.79
    beans
    -0.77
     Annotations
    -0.74
    ulic
    -0.72
    uzz
    -0.72
    ITED
    -0.71
    anwhile
    -0.71
     Beans
    -0.71
     Mush
    -0.70
    din
    -0.70
    POSITIVE LOGITS
     sexes
    0.81
     side
    0.80
     extremes
    0.80
     scenario
    0.76
     sex
    0.76
    osite
    0.75
    hesis
    0.74
     sides
    0.73
     direction
    0.72
     gender
    0.71
    Activations Density 0.031%

    No Known Activations