© 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. 7-RES-JB
    11. 12515
    Prev
    Next
    INDEX
    Explanations

    descriptions of accidents and disasters

    oai_token-act-pair · gpt-3.5-turbo

    events involving accidents or disasters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     promotions
    -0.72
    ante
    -0.70
     promotion
    -0.70
     paternal
    -0.69
     alphabet
    -0.69
    sense
    -0.68
    onomy
    -0.68
    ħĭ
    -0.67
    paren
    -0.67
    otics
    -0.64
    POSITIVE LOGITS
     injuring
    0.96
    result
    0.90
     resulting
    0.90
     ensuing
    0.89
     resultant
    0.89
     Luckily
    0.86
     eruption
    0.85
     ensued
    0.85
     inciner
    0.85
     screamed
    0.83
    Activations Density 0.777%

    No Known Activations