© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 6-RES-JB
    11. 17689
    Prev
    Next
    INDEX
    Explanations

    phrases related to causes of death

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating causes of death

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    eele
    -0.88
    oyer
    -0.75
    Enabled
    -0.71
    signed
    -0.71
    Union
    -0.70
    Square
    -0.69
    andowski
    -0.69
    alore
    -0.69
     backdrop
    -0.68
     Cosponsors
    -0.68
    POSITIVE LOGITS
     illness
    0.98
     overdoses
    0.94
     overdose
    0.92
     exhaustion
    0.87
     pneumonia
    0.86
     gunshot
    0.85
     poisoning
    0.84
     illnesses
    0.83
     suicide
    0.81
     starvation
    0.81
    Activations Density 0.099%

    No Known Activations