© 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. 12069
    Prev
    Next
    INDEX
    Explanations

    instances where someone is making a decision based on weighing potential risks

    oai_token-act-pair · gpt-3.5-turbo
    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
    ļéĨĴ
    -0.77
    visory
    -0.77
    ãĥĥãĥĪ
    -0.75
    scribe
    -0.74
    emaker
    -0.71
    blem
    -0.70
    cedented
    -0.70
    vance
    -0.70
    ãĥ¥
    -0.69
    ãĤ¨ãĥ«
    -0.69
    POSITIVE LOGITS
     huh
    0.97
     albeit
    0.95
     somew
    0.92
     eh
    0.91
     but
    0.80
     yeah
    0.77
     maybe
    0.76
     haha
    0.76
     nevertheless
    0.73
     Anyway
    0.70
    Activations Density 0.307%

    No Known Activations