© 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. 2854
    Prev
    Next
    INDEX
    Explanations

    information related to technology products and specifications

    oai_token-act-pair · gpt-3.5-turbo

    references to gaming hardware and related technology

    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
    terness
    -0.82
    hyde
    -0.80
    hirt
    -0.80
    nown
    -0.77
    Filename
    -0.75
    potion
    -0.75
    undo
    -0.74
    ļéĨĴ
    -0.74
    job
    -0.74
    =-=-
    -0.73
    POSITIVE LOGITS
     laptops
    1.71
     smartphones
    1.66
     TVs
    1.63
     computers
    1.56
     PCs
    1.51
     automobiles
    1.50
     notebooks
    1.47
     telev
    1.47
     phones
    1.46
     cars
    1.45
    Activations Density 0.326%

    No Known Activations