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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 18299
    Prev
    Next
    INDEX
    Explanations

    words related to respectability or admiration

    oai_token-act-pair · gpt-3.5-turbo

    terms related to quality indicators, specifically those denoting respectability, mediocrity, and misery

    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
     timelines
    -0.83
    ode
    -0.74
     timeline
    -0.73
     ï
    -0.69
    angelo
    -0.68
     Timeline
    -0.68
     Array
    -0.67
     triggers
    -0.65
    ï
    -0.64
    iton
    -0.64
    POSITIVE LOGITS
     respectable
    2.85
    iddling
    1.83
     mediocre
    1.66
     decent
    1.63
     honorable
    1.49
     miserable
    1.48
     competent
    1.37
     lowly
    1.37
     sane
    1.30
     satisfactory
    1.28
    Activations Density 0.033%

    No Known Activations