© 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. 8-RES-JB
    11. 10884
    Prev
    Next
    INDEX
    Explanations

    keywords related to the real estate and construction industry, particularly focusing on condominiums

    oai_token-act-pair · gpt-3.5-turbo

    specific nouns related to various contexts, particularly architectural terms and catastrophic events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Nap
    -0.75
     iT
    -0.72
    Ros
    -0.72
    BIT
    -0.70
    OVER
    -0.69
    OSP
    -0.69
    Pir
    -0.68
    Journal
    -0.68
    Veter
    -0.66
    Pak
    -0.66
    POSITIVE LOGITS
    phrine
    0.84
    clude
    0.79
     tails
    0.72
    kered
    0.70
    zed
    0.67
    zes
    0.66
    ization
    0.65
     affair
    0.65
    ary
    0.64
    ced
    0.64
    Activations Density 0.239%

    No Known Activations