© 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. 8578
    Prev
    Next
    INDEX
    Explanations

    text related to planning and outlines

    oai_token-act-pair · gpt-3.5-turbo

    content related to planning and organization

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    owered
    -0.71
     tainted
    -0.68
    cens
    -0.67
     spurious
    -0.67
    Lic
    -0.66
     Laugh
    -0.66
     independents
    -0.66
     Licensed
    -0.66
     tarn
    -0.65
    rage
    -0.65
    POSITIVE LOGITS
     plan
    1.43
     planner
    1.40
     checklist
    1.37
    Plan
    1.30
     planning
    1.30
    plan
    1.27
     Planning
    1.24
     contingency
    1.22
     schedules
    1.22
     plans
    1.21
    Activations Density 0.706%

    No Known Activations