© 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. 7-RES-JB
    11. 1857
    Prev
    Next
    INDEX
    Explanations

    words related to the surname "Duchamp"

    oai_token-act-pair · gpt-3.5-turbo

    references to the term "Duch," likely related to individuals or entities with that name

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     diminishing
    -0.65
     eaves
    -0.65
    wcs
    -0.63
     tampering
    -0.63
     contrace
    -0.62
     primed
    -0.59
     Wass
    -0.58
     cir
    -0.56
    GMT
    -0.55
    xtap
    -0.55
    POSITIVE LOGITS
    icago
    1.22
    anan
    1.01
    atile
    0.82
    onne
    0.82
    igan
    0.82
    arist
    0.80
    itect
    0.80
    inas
    0.78
    atters
    0.78
    enance
    0.75
    Activations Density 0.020%

    No Known Activations