© 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. 17282
    Prev
    Next
    INDEX
    Explanations

    topics related to government, politics, economics, and finance

    oai_token-act-pair · gpt-3.5-turbo

    topics related to governance, economics, and politics

    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
    é¾įåĸļ士
    -0.80
    lyak
    -0.76
    "))
    -0.72
     Furious
    -0.70
    ++++
    -0.69
    ATURES
    -0.69
    thodox
    -0.69
     Tooth
    -0.69
    ealous
    -0.68
    eus
    -0.67
    POSITIVE LOGITS
    gallery
    0.75
    allery
    0.66
     aust
    0.65
    ownt
    0.64
    battle
    0.63
     arts
    0.62
     Tud
    0.62
     pav
    0.59
    cent
    0.59
    rad
    0.59
    Activations Density 0.035%

    No Known Activations