© 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. 6-RES-JB
    11. 12070
    Prev
    Next
    INDEX
    Explanations

    aesthetic or artistic descriptions, particularly related to architecture and sculpture

    oai_token-act-pair · gpt-3.5-turbo

    terms related to art and aesthetics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    aucus
    -0.69
    lees
    -0.69
    bern
    -0.69
    lee
    -0.68
    yip
    -0.67
    unker
    -0.67
    verning
    -0.66
    zee
    -0.66
    DN
    -0.65
     Lethal
    -0.65
    POSITIVE LOGITS
     aesthetic
    1.22
     artwork
    1.21
     sculpture
    1.18
     aesthetics
    1.16
     art
    1.12
     sculptures
    1.09
     paintings
    1.07
     decoration
    1.07
     painter
    1.07
     architectural
    1.00
    Activations Density 0.232%

    No Known Activations