© 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. 1175
    Prev
    Next
    INDEX
    Explanations

    what's the opposing viewpoint or contrast in a sentence

    oai_token-act-pair · gpt-3.5-turbo

    instances of contrasting phrases introduced by "on the other hand."

    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
     Berger
    -0.56
    lessly
    -0.54
     Pastor
    -0.54
     Classification
    -0.53
    burg
    -0.52
    1971
    -0.52
     asleep
    -0.52
     Dollars
    -0.52
    anners
    -0.51
     reproduce
    -0.51
    POSITIVE LOGITS
     side
    1.17
    worldly
    1.02
     hand
    0.94
     hemisphere
    0.89
     periphery
    0.84
    Side
    0.83
     sides
    0.81
     occasions
    0.81
     Side
    0.81
    side
    0.81
    Activations Density 0.017%

    No Known Activations