© 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. 13634
    Prev
    Next
    INDEX
    Explanations

    medical or safety-related terms indicating precautionary measures or processes

    oai_token-act-pair · gpt-3.5-turbo

    terms related to precautions and safety measures

    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
    soever
    -0.76
    cloth
    -0.67
    pace
    -0.65
    NetMessage
    -0.63
     Kush
    -0.61
     Âł Âł Âł Âł
    -0.61
    ----------
    -0.61
    >>>>>>>>
    -0.60
    âĺħâĺħ
    -0.60
     darn
    -0.59
    POSITIVE LOGITS
    ary
    2.56
    aries
    2.04
    arily
    1.92
    ation
    1.81
    ARY
    1.71
    alist
    1.71
    ality
    1.67
    ally
    1.66
    naire
    1.61
    als
    1.55
    Activations Density 0.222%

    No Known Activations