© 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. 4-RES-JB
    11. 22148
    Prev
    Next
    INDEX
    Explanations

    references to levels, amounts, or extents of something

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "degree" indicating varying levels of intensity or measurement

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

    No Comments

    Negative Logits
    miah
    -0.76
    theless
    -0.70
     Bans
    -0.69
    sels
    -0.69
    ãģĮ
    -0.65
     Tanz
    -0.64
    BY
    -0.64
     Tosh
    -0.64
    imen
    -0.63
    lisher
    -0.62
    POSITIVE LOGITS
     degree
    0.95
     degrees
    0.93
     Celsius
    0.87
     Degree
    0.80
    uates
    0.78
    llor
    0.78
     attainment
    0.76
     Fahrenheit
    0.73
     Deg
    0.72
    ance
    0.70
    Activations Density 0.010%

    No Known Activations