© 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. 11-RES-JB
    11. 2188
    Prev
    Next
    INDEX
    Explanations

    entities and phrases related to natural disasters and recovery efforts, as well as governmental responses to such events

    oai_token-act-pair · gpt-3.5-turbo

    terms related to disaster recovery and government response

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Chess
    -0.94
     Weasley
    -0.92
     chess
    -0.91
    ovo
    -0.90
    furt
    -0.86
    hig
    -0.85
    ovan
    -0.85
     transsexual
    -0.83
     testosterone
    -0.82
    IQ
    -0.81
    POSITIVE LOGITS
     FEMA
    1.86
     hurricane
    1.85
     hurricanes
    1.74
     Hurricane
    1.72
     Katrina
    1.66
     landfall
    1.63
     flooding
    1.60
     flood
    1.58
    Hur
    1.58
     Irma
    1.54
    Activations Density 0.607%

    No Known Activations