© 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. 6-RES-JB
    11. 10722
    Prev
    Next
    INDEX
    Explanations

    phrases indicating opting out of agreements or services

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to options or choices in agreements and consent

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     pulp
    -0.66
     Henderson
    -0.65
     Rath
    -0.63
     bis
    -0.62
     Hunger
    -0.62
     Moj
    -0.62
     Mour
    -0.61
     Galile
    -0.61
     Burr
    -0.60
     Lau
    -0.60
    POSITIVE LOGITS
    cert
    0.94
    ship
    0.93
    operated
    0.89
    ships
    0.89
    coded
    0.89
    lease
    0.88
    items
    0.88
    ature
    0.87
    to
    0.87
    agent
    0.85
    Activations Density 0.106%

    No Known Activations