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. 10-RES-JB
    6. 22637
    Prev
    Next
    INDEX
    Explanations

    phrases or words related to damage or destruction caused by various events

    oai_token-act-pair · gpt-3.5-turbo

    references to destruction or damage caused by external forces

    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
    Favorite
    -0.92
    CLASSIFIED
    -0.81
    inea
    -0.78
    actly
    -0.72
    pring
    -0.71
    IGN
    -0.70
    Interview
    -0.69
    istry
    -0.69
    ODY
    -0.69
    Registered
    -0.68
    POSITIVE LOGITS
     storms
    1.48
     floods
    1.47
     earthquakes
    1.41
     rains
    1.40
     landsl
    1.38
     wildfires
    1.38
     drought
    1.35
     flooding
    1.33
     earthquake
    1.33
     Hurricane
    1.30
    Activations Density 0.408%

    No Known Activations