© 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. 14856
    Prev
    Next
    INDEX
    Explanations

    the word "live" in various contexts, such as living arrangements, lifestyle choices, or life philosophies

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "live" in various contexts

    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
    elight
    -0.88
    essee
    -0.87
    sonian
    -0.86
    uyomi
    -0.81
    unity
    -0.79
    aneers
    -0.79
    enei
    -0.78
    intendent
    -0.78
    umen
    -0.78
    ery
    -0.77
    POSITIVE LOGITS
    lihood
    0.94
     Wage
    0.82
     vic
    0.74
    stead
    0.74
    journal
    0.73
     liv
    0.73
     lives
    0.72
     Living
    0.72
    hart
    0.71
     living
    0.70
    Activations Density 0.030%

    No Known Activations