© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 12-RES-JB
    11. 4117
    Prev
    Next
    INDEX
    Explanations

    adjectives related to abilities or achievements

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    terms related to authority, power, and status

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 12-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_post
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Outbreak
    -0.75
     Correction
    -0.73
    DAQ
    -0.72
    USS
    -0.72
     Thoughts
    -0.71
     Scenes
    -0.71
     Notting
    -0.70
     COP
    -0.70
     Attention
    -0.70
    RD
    -0.68
    POSITIVE LOGITS
     outweigh
    1.39
     outwe
    1.30
     trump
    1.10
     dwind
    1.06
     evapor
    1.05
     preclude
    1.01
     disqual
    0.99
     overshadow
    0.99
     rested
    0.95
     belie
    0.93
    Activations Density 0.284%

    No Known Activations