© 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. 0-RES-JB
    11. 12092
    Prev
    Next
    INDEX
    Explanations

    keywords related to reporting or news

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "Report" and its variations, indicating a focus on reporting or news-related content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     choices
    -0.69
     convenience
    -0.69
     longevity
    -0.68
     expansion
    -0.68
     art
    -0.67
     styl
    -0.66
     cosmetic
    -0.66
     Nec
    -0.65
     punk
    -0.64
     fun
    -0.64
    POSITIVE LOGITS
    Report
    4.10
    report
    2.70
    Reports
    2.22
    reports
    2.03
    Reporting
    1.85
     REPORT
    1.64
     Report
    1.64
    reporting
    1.55
     report
    1.48
    reported
    1.37
    Activations Density 0.010%

    No Known Activations