© 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. 8-RES-JB
    11. 3316
    Prev
    Next
    INDEX
    Explanations

    phrases indicating the need to wait or take some action in the future

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate necessity or obligation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Recommended
    -0.71
     Glad
    -0.68
    Motion
    -0.65
     Kara
    -0.65
     Lif
    -0.65
     Ambro
    -0.65
     Abram
    -0.64
     Milky
    -0.63
     Victims
    -0.60
     Ideal
    -0.59
    POSITIVE LOGITS
     wait
    1.15
     rethink
    1.13
     reconsider
    0.93
     revise
    0.91
     rely
    0.90
     settle
    0.90
     endure
    0.88
     reckon
    0.85
     intervene
    0.84
     convince
    0.84
    Activations Density 0.091%

    No Known Activations