Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 8-RES-JB
    6. 8
    Prev
    Next
    INDEX
    Explanations

    natural disasters and their aftermath

    oai_token-act-pair · gpt-3.5-turbo

    negative environmental impacts or disasters caused by natural events

    oai_token-act-pair · gpt-4o-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
    onomy
    -0.94
    IQ
    -0.85
    names
    -0.80
    itles
    -0.77
    Privacy
    -0.76
    uity
    -0.76
    Clar
    -0.75
    onyms
    -0.74
    istry
    -0.74
    anda
    -0.73
    POSITIVE LOGITS
     combustion
    1.28
     bombardment
    1.22
     eruption
    1.21
     earthquakes
    1.21
     earthquake
    1.19
     volcanic
    1.18
     explosions
    1.17
     storms
    1.17
     rains
    1.12
     hurricanes
    1.12
    Activations Density 0.568%

    No Known Activations