© 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. 10-RES-JB
    11. 16039
    Prev
    Next
    INDEX
    Explanations

    words related to crises or serious issues

    oai_token-act-pair · gpt-3.5-turbo

    language related to crises and their impacts on society

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     representations
    -0.74
    endment
    -0.73
     conversions
    -0.68
     dab
    -0.64
     promotional
    -0.64
    urai
    -0.64
     nods
    -0.63
     Creed
    -0.63
     accur
    -0.62
     nic
    -0.62
    POSITIVE LOGITS
     worsened
    1.36
     worsen
    1.27
     engulf
    1.19
     exacerbated
    1.18
     worsening
    1.13
     plag
    1.08
     aggravated
    1.03
     epidemic
    1.01
     compounded
    1.00
     severity
    0.99
    Activations Density 0.478%

    No Known Activations