© 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. 11482
    Prev
    Next
    INDEX
    Explanations

    commands or instructions starting with "To"

    oai_token-act-pair · gpt-3.5-turbo

    the word "To" indicating intent or direction

    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
    soDeliveryDate
    -0.77
     taps
    -0.70
     looms
    -0.63
     shaping
    -0.61
    _.
    -0.60
     til
    -0.59
     disappro
    -0.59
     affecting
    -0.58
    SpaceEngineers
    -0.58
     costing
    -0.58
    POSITIVE LOGITS
    ilet
    1.32
    asty
    1.01
     summarize
    0.98
    pping
    0.91
    ilers
    0.90
     celebrate
    0.88
     conserve
    0.86
     maximize
    0.86
     clarify
    0.85
    ffee
    0.85
    Activations Density 0.141%

    No Known Activations