© 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. 20360
    Prev
    Next
    INDEX
    Explanations

    phrases related to emphasizing the importance of noting something

    oai_token-act-pair · gpt-3.5-turbo

    phrases that emphasize the importance of specific actions or considerations

    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
    ãĤ¦ãĤ¹
    -0.87
    soever
    -0.80
    til
    -0.69
    ãģ®å
    -0.69
    º
    -0.68
    ridden
    -0.67
    ieu
    -0.67
    bryce
    -0.65
    jury
    -0.65
    ELD
    -0.65
    POSITIVE LOGITS
     note
    1.38
     understand
    1.31
     remember
    1.31
     emphasize
    1.30
     distinguish
    1.25
     realize
    1.25
     realise
    1.24
     differentiate
    1.21
     recognize
    1.18
     clarify
    1.16
    Activations Density 0.098%

    No Known Activations