© 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. 22898
    Prev
    Next
    INDEX
    Explanations

    mentions of accidents or disasters

    oai_token-act-pair · gpt-3.5-turbo

    references to accidents and casualties

    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
    ophy
    -0.72
    Intern
    -0.69
    uchin
    -0.66
    oliberal
    -0.66
    utical
    -0.64
    angel
    -0.64
    idel
    -0.63
     butterflies
    -0.61
    emonic
    -0.60
     contractual
    -0.59
    POSITIVE LOGITS
     spree
    1.05
     occurred
    1.04
     happened
    0.97
     perpetrated
    0.85
     sparked
    0.82
     involving
    0.80
     stemmed
    0.79
     victims
    0.79
     unfold
    0.79
     unfolded
    0.78
    Activations Density 0.220%

    No Known Activations