© 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. 7-RES-JB
    11. 11074
    Prev
    Next
    INDEX
    Explanations

    health-related conditions leading to death

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to causes of death or medical conditions

    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
    soDeliveryDate
    -0.82
    oyer
    -0.81
    soType
    -0.80
     Cosponsors
    -0.79
    Enabled
    -0.75
    utical
    -0.72
    uman
    -0.71
    ctor
    -0.66
    yssey
    -0.65
    OH
    -0.65
    POSITIVE LOGITS
     gunshot
    1.07
     overdoses
    1.05
     overdose
    1.01
     suicide
    1.01
     illness
    0.96
     starvation
    0.95
     gunfire
    0.91
     exhaustion
    0.90
     pneumonia
    0.87
     poisoning
    0.86
    Activations Density 0.081%

    No Known Activations