© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 11-RES-JB
    11. 14980
    Prev
    Next
    INDEX
    Explanations

    words related to planning and decision-making

    oai_token-act-pair · gpt-3.5-turbo

    references to planning and decision-making processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    olor
    -0.76
    ugu
    -0.75
     redd
    -0.73
    ©¶æ¥µ
    -0.73
    Roy
    -0.71
    Lic
    -0.71
     Liberties
    -0.70
     Cosponsors
    -0.70
    Touch
    -0.68
    abilia
    -0.67
    POSITIVE LOGITS
     plan
    1.82
    Plan
    1.79
     planning
    1.78
     planner
    1.74
     planners
    1.67
    plan
    1.67
     plans
    1.62
     Plan
    1.60
     Planning
    1.58
     planned
    1.55
    Activations Density 0.678%

    No Known Activations