© 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. 24446
    Prev
    Next
    INDEX
    Explanations

    phrases indicating agreement to terms and conditions

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to user agreement and consent in terms of privacy and policies

    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
    ilts
    -0.61
     glim
    -0.60
    oster
    -0.60
    amina
    -0.58
    ngth
    -0.57
    iculture
    -0.57
    mania
    -0.55
    ONES
    -0.54
    gins
    -0.54
    ordinary
    -0.54
    POSITIVE LOGITS
    itivity
    0.68
     {{
    0.65
     thereto
    0.64
    iliate
    0.63
    taboola
    0.61
    emn
    0.59
     Hilbert
    0.59
     to
    0.58
    20439
    0.56
    ettings
    0.56
    Activations Density 0.025%

    No Known Activations