© 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. 0-RES-JB
    11. 15026
    Prev
    Next
    INDEX
    Explanations

    words related to the name "Burns"

    oai_token-act-pair · gpt-3.5-turbo

    the name "Burns" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Atl
    -0.73
    itude
    -0.70
    FN
    -0.67
     asymm
    -0.67
    eu
    -0.66
     Atl
    -0.65
    GU
    -0.65
    Tile
    -0.65
     sql
    -0.65
     anten
    -0.64
    POSITIVE LOGITS
     Burns
    4.05
    Burn
    1.67
     Burn
    1.48
     Burnett
    1.47
     burns
    1.40
    burn
    1.26
     Springfield
    1.21
     Stevens
    1.21
     Burning
    1.19
     Homer
    1.13
    Activations Density 0.012%

    No Known Activations