© 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. 0-RES-JB
    11. 16523
    Prev
    Next
    INDEX
    Explanations

    phrases related to the concept of "lifetime."

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    oit
    -0.70
    anks
    -0.69
     Apart
    -0.64
    ucci
    -0.63
    vill
    -0.60
    grass
    -0.60
    clair
    -0.60
    asia
    -0.59
     annex
    -0.59
    oka
    -0.59
    POSITIVE LOGITS
     lifetime
    4.13
     Lifetime
    2.74
     lifespan
    1.78
     lif
    1.75
    lif
    1.69
     lifelong
    1.62
    etimes
    1.51
     life
    1.15
     LIFE
    1.12
     career
    1.07
    Activations Density 0.021%

    No Known Activations