© 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. 11-RES-JB
    11. 22118
    Prev
    Next
    INDEX
    Explanations

    words related to opting out or agreement in a terms and conditions context

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to subscription and opt-out options

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Leilan
    -0.61
     mosqu
    -0.58
    esville
    -0.56
    ngth
    -0.56
    emale
    -0.55
     Dak
    -0.55
    ighting
    -0.54
     oun
    -0.54
     tiss
    -0.52
     coh
    -0.52
    POSITIVE LOGITS
     opt
    0.65
     versa
    0.62
    thumbnails
    0.62
    Subscribe
    0.61
    rame
    0.61
    -
    0.58
    nir
    0.58
    ificate
    0.58
    ifies
    0.57
     Oops
    0.57
    Activations Density 0.010%

    No Known Activations