© 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. 7208
    Prev
    Next
    INDEX
    Explanations

    phrases related to future planning or decision-making

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "planning."

    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
    inas
    -0.86
    upon
    -0.74
    adr
    -0.72
     Jude
    -0.70
    osi
    -0.65
     Chin
    -0.65
     Amos
    -0.65
    early
    -0.63
     Sanctuary
    -0.63
    bal
    -0.63
    POSITIVE LOGITS
     planning
    1.07
     planner
    0.95
    isphere
    0.89
     planners
    0.87
     plotting
    0.85
     lawy
    0.84
     recons
    0.75
     contrace
    0.75
     commissions
    0.74
     sessions
    0.74
    Activations Density 0.022%

    No Known Activations