© 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. 7-RES-JB
    11. 23520
    Prev
    Next
    INDEX
    Explanations

    various forms of advertisements

    oai_token-act-pair · gpt-3.5-turbo

    various forms of advertisements and promotional content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     brid
    -0.84
     choking
    -0.80
     appe
    -0.79
     spitting
    -0.76
     credential
    -0.76
     tram
    -0.75
     preservation
    -0.74
     hospitality
    -0.73
     honoured
    -0.73
     presumptive
    -0.72
    POSITIVE LOGITS
    Advertisements
    1.53
    Conclusion
    1.38
    Related
    1.32
    Topics
    1.30
    RAW
    1.30
    References
    1.26
    Lastly
    1.24
    Anyway
    1.23
    Loading
    1.23
    Finally
    1.22
    Activations Density 0.273%

    No Known Activations