© 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 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. 9-RES-JB
    11. 19660
    Prev
    Next
    INDEX
    Explanations

    sentence structures related to diplomatic or official statements

    oai_token-act-pair · gpt-3.5-turbo

    expressions of support and commitment to relationships or alliances

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     crap
    -0.78
     Craigslist
    -0.75
     shit
    -0.72
    shit
    -0.70
     hog
    -0.67
     Nope
    -0.67
     rm
    -0.66
    rm
    -0.66
     nipple
    -0.66
     lol
    -0.65
    POSITIVE LOGITS
     humanitarian
    1.06
     unity
    0.98
     diplomacy
    0.97
     strengthening
    0.90
     thanked
    0.90
     condolences
    0.90
     congratulations
    0.89
    ourage
    0.87
     congratulated
    0.87
     honour
    0.86
    Activations Density 0.614%

    No Known Activations