© 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. 11-RES-JB
    11. 3377
    Prev
    Next
    INDEX
    Explanations

    descriptions of physical attributes or characteristics, particularly related to appearance or construction

    oai_token-act-pair · gpt-3.5-turbo

    elements related to design and aesthetics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    =-=-=-=-
    -0.85
    iatus
    -0.84
    azine
    -0.83
    votes
    -0.82
    NPR
    -0.82
    agents
    -0.81
    dule
    -0.80
    Rate
    -0.79
    ername
    -0.77
    mination
    -0.77
    POSITIVE LOGITS
     sleek
    1.31
     elegant
    1.28
     classy
    1.26
     matte
    1.25
     vibrant
    1.25
     minimalist
    1.24
     luxurious
    1.23
     timeless
    1.23
     floral
    1.23
     vintage
    1.20
    Activations Density 0.369%

    No Known Activations