© 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. 11-RES-JB
    11. 7465
    Prev
    Next
    INDEX
    Explanations

    influences of international politics and geopolitical events

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating the collection and dissemination of information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    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
    ¬¼
    -0.76
    quished
    -0.73
    ãĤ¦ãĤ¹
    -0.72
    hed
    -0.70
    sted
    -0.68
    abouts
    -0.68
    EngineDebug
    -0.68
    TY
    -0.65
    VERTISEMENT
    -0.63
    forced
    -0.63
    POSITIVE LOGITS
     organize
    1.32
     eliminate
    1.30
     improve
    1.29
     create
    1.29
     formulate
    1.28
     stabilize
    1.28
     consolidate
    1.27
     establish
    1.27
     administer
    1.27
     cultivate
    1.26
    Activations Density 0.268%

    No Known Activations