© 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. 8-RES-JB
    11. 20448
    Prev
    Next
    INDEX
    Explanations

    phrases related to environmental disasters, specifically spills and their aftermath

    oai_token-act-pair · gpt-3.5-turbo

    references to environmental disasters, particularly oil spills

    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
    HCR
    -0.82
    tarians
    -0.70
    tarian
    -0.70
    olkien
    -0.68
    izons
    -0.66
    iterranean
    -0.64
    jee
    -0.64
    ieval
    -0.64
    eering
    -0.63
     Malays
    -0.63
    POSITIVE LOGITS
     spills
    0.91
     spill
    0.89
    overs
    0.87
    over
    0.85
     spilled
    0.84
    sheets
    0.79
    waters
    0.77
    age
    0.76
    OVER
    0.75
    field
    0.75
    Activations Density 0.056%

    No Known Activations