© 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. 11-RES-JB
    11. 11605
    Prev
    Next
    INDEX
    Explanations

    phrases related to fundamental principles or core values

    oai_token-act-pair · gpt-3.5-turbo

    phrases emphasizing central concepts or principles

    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
    estyles
    -0.78
    ograms
    -0.75
    reau
    -0.73
    TIT
    -0.71
    estones
    -0.71
    elaide
    -0.71
    igrants
    -0.70
    swick
    -0.69
    hran
    -0.68
    forts
    -0.67
    POSITIVE LOGITS
     modern
    1.01
     contemporary
    0.92
     capitalism
    0.85
     any
    0.85
     liberalism
    0.84
     conservatism
    0.82
     why
    0.82
     democracy
    0.81
     nutshell
    0.79
     owning
    0.78
    Activations Density 0.195%

    No Known Activations