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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 4-RES-JB
    11. 9674
    Prev
    Next
    INDEX
    Explanations

    words related to longevity and lifespan

    oai_token-act-pair · gpt-3.5-turbo

    terms related to longevity and lifespan

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

    No Comments

    Negative Logits
    unin
    -0.75
    Hyper
    -0.71
    eries
    -0.70
    Tonight
    -0.69
    anooga
    -0.69
    riad
    -0.68
    Border
    -0.67
    ãĥĥãĥī
    -0.66
     Cosponsors
    -0.65
    atchewan
    -0.64
    POSITIVE LOGITS
     lifespan
    1.09
     longevity
    1.06
     expectancy
    1.01
    jriwal
    0.86
    lihood
    0.84
     destro
    0.83
     surv
    0.82
    thood
    0.82
     durability
    0.80
     therap
    0.78
    Activations Density 0.020%

    No Known Activations