© 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. 18572
    Prev
    Next
    INDEX
    Explanations

    phrases related to technical issues or problems

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to apologies and customer service issues

    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
    pires
    -0.72
    chedel
    -0.71
     taboo
    -0.71
     indo
    -0.68
    igion
    -0.67
     intox
    -0.67
     dope
    -0.66
     juxtap
    -0.66
     ornament
    -0.66
     sidx
    -0.65
    POSITIVE LOGITS
     outage
    1.34
     workaround
    1.19
     refunds
    1.15
     impacted
    1.07
     fixes
    1.07
     remed
    1.06
     Fixes
    1.03
     affected
    1.02
     downtime
    1.00
     fix
    0.98
    Activations Density 0.466%

    No Known Activations