© 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. 8-RES-JB
    11. 1261
    Prev
    Next
    INDEX
    Explanations

    economic comparisons or ratios

    oai_token-act-pair · gpt-3.5-turbo

    phrases that quantify events or entities in relation to each other

    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
    ez
    -0.73
    Ü
    -0.73
    HCR
    -0.70
    ãĥ¯
    -0.69
    glers
    -0.68
     streng
    -0.68
    dict
    -0.67
    skirts
    -0.67
    folios
    -0.67
    Ú
    -0.65
    POSITIVE LOGITS
     conceivable
    1.03
    THING
    0.91
     dollar
    0.90
     ounce
    0.89
     imaginable
    0.85
     thousand
    0.79
     hundred
    0.77
     capita
    0.77
     succeeding
    0.77
     inch
    0.76
    Activations Density 0.041%

    No Known Activations