© 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. 7831
    Prev
    Next
    INDEX
    Explanations

    words related to authority and power

    oai_token-act-pair · gpt-3.5-turbo

    word stems related to political or governmental concepts

    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
     QC
    -0.61
     Perkins
    -0.60
     Buk
    -0.59
    hof
    -0.59
     Salem
    -0.58
     lag
    -0.57
     Cron
    -0.57
     elves
    -0.56
     Daly
    -0.56
    hower
    -0.55
    POSITIVE LOGITS
    raphic
    1.52
    rams
    1.25
    roups
    1.21
    raphics
    1.20
    roup
    1.19
    raph
    1.12
    allery
    1.05
    ravity
    1.04
    raf
    0.99
    istration
    0.98
    Activations Density 0.067%

    No Known Activations