© 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. 14711
    Prev
    Next
    INDEX
    Explanations

    mentions of specific countries and political events

    oai_token-act-pair · gpt-3.5-turbo

    punctuation marks, primarily periods

    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
     carbohyd
    -0.80
     transition
    -0.74
     integ
    -0.73
     complementary
    -0.72
     isot
    -0.72
     heavily
    -0.70
     interpreter
    -0.70
     extensively
    -0.70
     proport
    -0.69
     advoc
    -0.69
    POSITIVE LOGITS
     Nope
    1.39
     Instead
    1.31
     Surely
    1.30
     Or
    1.24
     Maybe
    1.22
     Alas
    1.21
     Wouldn
    1.20
     Perhaps
    1.16
     Sure
    1.15
     Somehow
    1.15
    Activations Density 0.491%

    No Known Activations