© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 8-RES-JB
    11. 13152
    Prev
    Next
    INDEX
    Explanations

    words related to weather and natural disasters

    oai_token-act-pair · gpt-3.5-turbo

    references to severe weather conditions and their impacts

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
     Founding
    -0.76
     Intellectual
    -0.75
     liberty
    -0.72
    duino
    -0.71
     Idol
    -0.71
     Patent
    -0.71
     Token
    -0.68
    Reviewer
    -0.68
     Nobel
    -0.68
     Socrates
    -0.68
    POSITIVE LOGITS
     gust
    1.00
     earthqu
    0.97
    storms
    0.96
     swept
    0.92
     pounded
    0.92
     lashed
    0.90
     winds
    0.90
     rains
    0.90
     showers
    0.89
     caused
    0.88
    Activations Density 0.201%

    No Known Activations