© 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. 9-RES-JB
    11. 23872
    Prev
    Next
    INDEX
    Explanations

    phrases related to enhancing or improving various aspects, such as biodiversity, student achievement, business profitability, and productivity

    oai_token-act-pair · gpt-3.5-turbo

    conjunctions and positive correlations related to improvement and effectiveness in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    wic
    -1.04
    quished
    -0.93
     Bastard
    -0.81
     Cosponsors
    -0.78
    oteric
    -0.76
     Merlin
    -0.76
     Cornel
    -0.71
    DragonMagazine
    -0.69
     Married
    -0.69
    uta
    -0.68
    POSITIVE LOGITS
     productivity
    1.14
     competitiveness
    1.12
     thereby
    1.06
     consequently
    1.04
     hence
    1.04
     profitability
    1.03
     cohesion
    1.02
     responsiveness
    1.00
     reduce
    1.00
     longevity
    0.98
    Activations Density 0.247%

    No Known Activations