© 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. 10-RES-JB
    11. 824
    Prev
    Next
    INDEX
    Explanations

    phrases related to activism, social issues, and political events

    oai_token-act-pair · gpt-3.5-turbo

    references to significant numbers or quantities related to events or conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    TPP
    -0.87
     [+
    -0.72
    obyl
    -0.72
    worth
    -0.71
    Rated
    -0.69
    govtrack
    -0.68
    EngineDebug
    -0.67
    ueller
    -0.67
    intent
    -0.67
    arez
    -0.67
    POSITIVE LOGITS
     organisation
    1.31
     embattled
    1.23
     organization
    1.22
     agency
    1.22
     company
    1.17
     country
    1.15
     institution
    1.13
     autom
    1.10
     fledgling
    1.08
     nation
    1.05
    Activations Density 0.952%

    No Known Activations