© 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. 17526
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal terms and disclaimers

    oai_token-act-pair · gpt-3.5-turbo

    terms related to disclaimers, permissions, and affiliate disclosures

    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
    osphere
    -0.67
    abouts
    -0.65
     Spiel
    -0.63
    ropolis
    -0.62
    llan
    -0.61
    rez
    -0.61
    ings
    -0.61
    tail
    -0.59
    gress
    -0.59
    meal
    -0.58
    POSITIVE LOGITS
    claimer
    0.81
    Disclaimer
    0.77
    çīĪ
    0.76
    Supported
    0.75
     disclaimer
    0.73
    Policy
    0.71
     permission
    0.71
     agreements
    0.69
    ilst
    0.66
     terms
    0.66
    Activations Density 0.083%

    No Known Activations