© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 8684
    Prev
    Next
    INDEX
    Explanations

    phrases related to construction and renovation

    oai_token-act-pair · gpt-3.5-turbo

    references to construction and building materials

    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
     Represent
    -0.81
     Discord
    -0.80
    IQ
    -0.80
    Chat
    -0.78
    Favorite
    -0.78
     Libertarian
    -0.78
    mopolitan
    -0.75
     Gifts
    -0.75
     Likes
    -0.75
    yip
    -0.74
    POSITIVE LOGITS
     excav
    1.38
     excavation
    1.37
     repairs
    1.35
     demolition
    1.29
     drainage
    1.27
     weld
    1.26
     bulldo
    1.24
     welding
    1.23
     repairing
    1.22
     debris
    1.21
    Activations Density 1.026%

    No Known Activations