© 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. 7641
    Prev
    Next
    INDEX
    Explanations

    phrases related to delays, interruptions, and setbacks

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to changes in status or events being hindered

    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
    oyal
    -0.56
    orescence
    -0.56
    nih
    -0.56
    vernment
    -0.54
    herence
    -0.52
    geries
    -0.51
    unciation
    -0.50
    ogue
    -0.50
    osen
    -0.50
    ascript
    -0.49
    POSITIVE LOGITS
     alot
    1.10
     due
    1.04
     lately
    1.02
     midway
    0.91
     earlier
    0.87
     sooner
    0.86
     tho
    0.86
     AFTER
    0.86
     recently
    0.85
     bc
    0.84
    Activations Density 0.632%

    No Known Activations