© 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. 9-RES-JB
    11. 7275
    Prev
    Next
    INDEX
    Explanations

    words related to conflict and geopolitical events

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "the"

    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
    roo
    -0.79
    ptr
    -0.77
     âĢº
    -0.76
    atown
    -0.76
    ertation
    -0.76
    olicy
    -0.75
    etsy
    -0.75
    umblr
    -0.74
    Ear
    -0.72
    iversity
    -0.72
    POSITIVE LOGITS
     country
    1.27
     rebels
    1.24
     Kremlin
    1.23
     Kurds
    1.23
     Saudis
    1.22
     Syrian
    1.22
     jihadists
    1.19
     regime
    1.18
     embassy
    1.17
     Taliban
    1.17
    Activations Density 0.525%

    No Known Activations