© 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. 8525
    Prev
    Next
    INDEX
    Explanations

    phrases related to secrecy and clandestine activities

    oai_token-act-pair · gpt-3.5-turbo

    references to controversial or violent historical events

    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
    estamp
    -0.81
    phies
    -0.73
    notes
    -0.69
     Tuls
    -0.69
     Highlights
    -0.67
     subtitles
    -0.67
     Lastly
    -0.66
     Rosenstein
    -0.65
    Points
    -0.64
    coins
    -0.63
    POSITIVE LOGITS
     operation
    1.23
     workings
    1.16
     operations
    1.13
     endeavor
    1.04
     bureaucracy
    1.03
     enterprise
    1.03
     underworld
    1.02
     scheme
    1.01
     regimen
    1.00
     warfare
    0.99
    Activations Density 0.805%

    No Known Activations