© 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. 11-RES-JB
    11. 1179
    Prev
    Next
    INDEX
    Explanations

    words related to an increase or improvement in various aspects such as defense, economics, public services, and government

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to the concept of "increased" in various contexts

    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
    aughs
    -0.74
    mad
    -0.72
    Stage
    -0.71
    another
    -0.70
    Complete
    -0.70
    wreck
    -0.70
    facts
    -0.70
    raid
    -0.69
    icably
    -0.68
    aceae
    -0.67
    POSITIVE LOGITS
     scrutiny
    1.27
     reliance
    1.24
     emphasis
    1.22
     visibility
    1.19
     transparency
    1.19
     flexibility
    1.18
     awareness
    1.17
     availability
    1.13
     vigilance
    1.08
     cooperation
    1.08
    Activations Density 0.122%

    No Known Activations