© 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. 9-RES-JB
    11. 7220
    Prev
    Next
    INDEX
    Explanations

    phrases related to national identity and values

    oai_token-act-pair · gpt-3.5-turbo

    themes related to freedom and opportunity within a society

    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
    study
    -0.67
     Feather
    -0.65
     Sequence
    -0.64
    NV
    -0.64
     Sites
    -0.64
     route
    -0.64
    soDeliveryDate
    -0.63
    bilt
    -0.62
     Helpful
    -0.62
     aft
    -0.62
    POSITIVE LOGITS
     ideals
    0.95
    pires
    0.86
     dictators
    0.83
     traditions
    0.82
     democracy
    0.80
     intellectuals
    0.79
     itself
    0.79
     mistrust
    0.79
     ideologies
    0.79
     totalitarian
    0.79
    Activations Density 0.773%

    No Known Activations