© 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. 1-RES-JB
    11. 14440
    Prev
    Next
    INDEX
    Explanations

    words related to making decisions, particularly when the decisions are important or impactful

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to decision-making processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    amina
    -0.77
     Dak
    -0.73
    nic
    -0.72
    vae
    -0.70
    rome
    -0.69
    amen
    -0.68
    rake
    -0.66
    jew
    -0.66
    rica
    -0.66
    uum
    -0.63
    POSITIVE LOGITS
     decisions
    1.36
     choices
    0.99
     decision
    0.94
     makers
    0.77
     ACTIONS
    0.77
     levers
    0.75
     stances
    0.74
     calculus
    0.74
    ulkan
    0.70
     regarding
    0.70
    Activations Density 0.015%

    No Known Activations