© 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. 10-RES-JB
    11. 3027
    Prev
    Next
    INDEX
    Explanations

    adjectives with a positive connotation

    oai_token-act-pair · gpt-3.5-turbo

    descriptors related to seriousness and quality of subjects discussed

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    xit
    -0.84
    thood
    -0.79
    arser
    -0.78
    elines
    -0.76
    hner
    -0.72
    algia
    -0.70
    mbudsman
    -0.68
    arer
    -0.67
    ichever
    -0.67
    ILA
    -0.66
    POSITIVE LOGITS
     indeed
    1.15
     (~
    0.98
     (>
    0.97
     sounding
    0.84
     thing
    0.78
     nowadays
    0.77
     affair
    0.75
     considering
    0.74
     stuff
    0.74
     (<
    0.73
    Activations Density 0.330%

    No Known Activations