© 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. 8-RES-JB
    11. 11246
    Prev
    Next
    INDEX
    Explanations

    references to the downfall or collapse of political structures

    oai_token-act-pair · gpt-3.5-turbo

    instances of societal collapse or decline

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Catalog
    -0.82
    fab
    -0.78
    rouse
    -0.77
    wcsstore
    -0.75
    >(
    -0.74
    URI
    -0.74
    nr
    -0.72
    FH
    -0.71
    ñ
    -0.70
    appropriately
    -0.70
    POSITIVE LOGITS
     civilizations
    0.94
     empires
    0.94
     civilization
    0.92
     civilisation
    0.85
     incumb
    0.81
     virginity
    0.78
     limbs
    0.78
     capitalism
    0.77
     dinosaurs
    0.77
     Prosper
    0.76
    Activations Density 0.178%

    No Known Activations