© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 3-RES-JB
    11. 17819
    Prev
    Next
    INDEX
    Explanations

    mentions of severe weather phenomena like storms, hurricanes, tornadoes, and typhoons

    oai_token-act-pair · gpt-3.5-turbo

    terms related to severe weather events and storms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    xus
    -0.73
    ļéĨĴ
    -0.72
    VO
    -0.71
    APTER
    -0.71
    nai
    -0.70
    xxxxxxxx
    -0.69
    CHO
    -0.68
     pawn
    -0.66
    pire
    -0.65
     pulp
    -0.65
    POSITIVE LOGITS
     rains
    1.20
     storms
    1.15
     rainfall
    1.08
    storms
    1.07
     weather
    1.02
     advis
    0.99
     impacts
    0.99
     winds
    0.98
     turbulence
    0.97
     hurricanes
    0.97
    Activations Density 0.089%

    No Known Activations