© 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. 20533
    Prev
    Next
    INDEX
    Explanations

    phrases related to dedication or commitment to a specific cause or purpose

    oai_token-act-pair · gpt-3.5-turbo

    recurrent themes and phrases centered around development and public policy

    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
    SPONSORED
    -0.92
    milo
    -0.78
    balls
    -0.74
    wind
    -0.74
    pants
    -0.69
    lins
    -0.68
    bats
    -0.67
    lan
    -0.66
    vious
    -0.65
    tops
    -0.64
    POSITIVE LOGITS
     advancement
    1.42
     dissemination
    1.32
     preservation
    1.31
     promotion
    1.30
     prevention
    1.29
     propagation
    1.29
     realization
    1.26
     attainment
    1.22
     formulation
    1.21
     development
    1.20
    Activations Density 0.200%

    No Known Activations