© 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. 2-RES-JB
    11. 369
    Prev
    Next
    INDEX
    Explanations

    words related to advocacy or support positions

    oai_token-act-pair · gpt-3.5-turbo

    the word "proponents"

    oai_token-act-pair · gpt-4-turbo

    references to supporters or advocates of various ideas or initiatives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    thur
    -0.75
    yss
    -0.71
     Peninsula
    -0.68
     Sul
    -0.68
    oÄŁ
    -0.67
     gorge
    -0.63
    away
    -0.62
     mountainous
    -0.62
     Himal
    -0.62
     Wonderland
    -0.61
    POSITIVE LOGITS
    ervatives
    0.98
     advocates
    0.92
     proponents
    0.87
     proponent
    0.85
    itutes
    0.84
    paces
    0.84
    sonian
    0.84
    itute
    0.80
    uggest
    0.79
    ervative
    0.79
    Activations Density 0.032%

    No Known Activations