© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 4-RES-JB
    11. 17333
    Prev
    Next
    INDEX
    Explanations

    references to the name "Bundy" in a specific context

    oai_token-act-pair · gpt-3.5-turbo

    references to the Bundy family and related locations or organizations

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

    No Comments

    Negative Logits
    akespeare
    -0.74
    oen
    -0.72
    odic
    -0.72
    apist
    -0.68
    ournal
    -0.67
    ORED
    -0.67
     ende
    -0.64
    omaly
    -0.64
    roach
    -0.63
    oppers
    -0.63
    POSITIVE LOGITS
     Bundy
    1.32
     ranch
    0.95
    querque
    0.78
     ranc
    0.78
     Ranch
    0.76
    anan
    0.73
     cattle
    0.73
    inez
    0.72
     heirs
    0.72
    hib
    0.71
    Activations Density 0.013%

    No Known Activations