© 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. 8-RES-JB
    11. 1886
    Prev
    Next
    INDEX
    Explanations

    words related to action or emphasis, particularly starting with 'pr'

    oai_token-act-pair · gpt-3.5-turbo

    words starting with "pr."

    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
    croft
    -0.68
     prolifer
    -0.65
     AMERICA
    -0.64
    BILITY
    -0.63
     field
    -0.62
     Sacrament
    -0.62
     Commodore
    -0.62
     Cheong
    -0.61
    rium
    -0.61
     bed
    -0.60
    POSITIVE LOGITS
    imate
    1.18
    imes
    1.17
    uning
    1.12
    udence
    1.12
    arians
    1.04
    ices
    1.02
    inters
    0.99
    anks
    0.99
    icks
    0.98
    atche
    0.98
    Activations Density 0.025%

    No Known Activations