© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 6964
    Prev
    Next
    INDEX
    Explanations

    time-related phrases such as "within 20 days" or "for a period of two months."

    oai_token-act-pair · gpt-3.5-turbo

    references to legal or regulatory time periods and requirements

    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
    æѦ
    -0.71
    士
    -0.66
    %%%%
    -0.62
    unk
    -0.61
     mathemat
    -0.58
    selage
    -0.55
    çļ
    -0.55
    /#
    -0.55
    NetMessage
    -0.54
    Stone
    -0.54
    POSITIVE LOGITS
     six
    1.10
     365
    1.04
     180
    1.03
     72
    1.02
     five
    0.97
     90
    0.97
     seven
    0.96
     twelve
    0.94
     24
    0.94
     three
    0.93
    Activations Density 0.249%

    No Known Activations