© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 10-RES-JB
    6. 6451
    Prev
    Next
    INDEX
    Explanations

    instances where actions are permitted or possible

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "can" and its variations, indicating potential actions or capabilities

    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
    interstitial
    -0.66
    existent
    -0.63
    ONSORED
    -0.62
     Mant
    -0.60
     intrig
    -0.60
     Matters
    -0.59
     Cooking
    -0.59
     Cortex
    -0.59
    quickShipAvailable
    -0.59
     Sandwich
    -0.59
    POSITIVE LOGITS
     choose
    1.24
     expect
    1.23
    't
    1.19
     optionally
    1.13
     easily
    1.06
     nominate
    1.05
     legally
    1.05
     freely
    1.05
     opt
    1.05
     submit
    1.02
    Activations Density 0.122%

    No Known Activations