© 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. 7-RES-JB
    11. 3184
    Prev
    Next
    INDEX
    Explanations

    statements where someone is advocating for a certain action or outcome

    oai_token-act-pair · gpt-3.5-turbo

    calls for action or requests related to various political or social issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    uded
    -0.68
    served
    -0.62
     Hale
    -0.62
    edin
    -0.62
     ®
    -0.61
     Unable
    -0.61
    fo
    -0.60
     LX
    -0.60
    fleet
    -0.59
     teased
    -0.59
    POSITIVE LOGITS
     abol
    0.87
     prayers
    0.81
     reconsider
    0.80
     stricter
    0.79
    psey
    0.76
     forgiveness
    0.75
     urgent
    0.73
     prayer
    0.72
     clarification
    0.72
     reinforcements
    0.70
    Activations Density 0.067%

    No Known Activations