© 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. 9581
    Prev
    Next
    INDEX
    Explanations

    words related to legal, political or social issues

    oai_token-act-pair · gpt-3.5-turbo
    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
    ruary
    -0.89
    AUT
    -0.83
    ellen
    -0.81
    ample
    -0.80
    pload
    -0.79
    ardless
    -0.78
    assis
    -0.77
    eddy
    -0.77
    matched
    -0.76
    oldemort
    -0.74
    POSITIVE LOGITS
     activities
    1.10
     activity
    1.04
     incidents
    1.01
     controversies
    0.95
     disruptions
    0.93
     behaviors
    0.92
     pursuits
    0.92
     disasters
    0.92
     endeavors
    0.91
     fatalities
    0.90
    Activations Density 0.029%

    No Known Activations