© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 0-RES-JB
    11. 16989
    Prev
    Next
    INDEX
    Explanations

    mentions of gaps or disparities in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    references to disparities or differences in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Rid
    -0.71
     Roses
    -0.67
    1001
    -0.67
    lander
    -0.67
     Lod
    -0.64
     recre
    -0.63
    rals
    -0.62
    enegger
    -0.61
    photos
    -0.60
    ctl
    -0.60
    POSITIVE LOGITS
     gap
    3.82
     gaps
    2.82
    gap
    2.43
     Gap
    2.23
     gulf
    1.97
     disparity
    1.86
     discrepancy
    1.84
     shortfall
    1.68
     loophole
    1.59
     mismatch
    1.57
    Activations Density 0.007%

    No Known Activations