© 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. 11-RES-JB
    11. 2307
    Prev
    Next
    INDEX
    Explanations

    references to the concept of death, particularly in the context of legal consequences

    oai_token-act-pair · gpt-3.5-turbo

    references to death and related concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    umar
    -0.70
    MN
    -0.69
    asma
    -0.67
    ullivan
    -0.65
     Wicked
    -0.64
    EEK
    -0.64
    ioned
    -0.62
    CN
    -0.59
     CLIENT
    -0.58
     Libre
    -0.58
    POSITIVE LOGITS
    bed
    1.08
     penalty
    1.05
     toll
    1.02
    blow
    1.01
     certificate
    0.99
     certificates
    0.96
     sentence
    0.95
     Penalty
    0.95
    adder
    0.93
     thro
    0.92
    Activations Density 0.047%

    No Known Activations