© 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. 2-RES-JB
    11. 22104
    Prev
    Next
    INDEX
    Explanations

    references to the name "Mundell"

    oai_token-act-pair · gpt-3.5-turbo

    references to specific individuals, particularly names associated with political or corporate contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    76561
    -0.80
    ãĤ·ãĥ£
    -0.78
    owers
    -0.72
    OHN
    -0.70
    dating
    -0.69
    uberty
    -0.69
    OPLE
    -0.69
    chnology
    -0.69
    ooters
    -0.68
    OWER
    -0.68
    POSITIVE LOGITS
     Mund
    0.90
    ality
    0.81
     mund
    0.78
     unden
    0.76
    isphere
    0.76
    nih
    0.75
    itary
    0.74
     concess
    0.72
    ano
    0.72
    hub
    0.72
    Activations Density 0.010%

    No Known Activations