Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 0-RES-JB
    6. 21205
    Prev
    Next
    INDEX
    Explanations

    mentions of the term "Live" that are relevant to television shows or events

    oai_token-act-pair · gpt-3.5-turbo

    occurrences 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 @ 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
     sack
    -0.73
    aeus
    -0.70
    orative
    -0.64
    atorial
    -0.64
    oiler
    -0.62
     manufact
    -0.61
     cartels
    -0.61
    dict
    -0.61
     draining
    -0.60
     brim
    -0.59
    POSITIVE LOGITS
     Live
    3.81
    Live
    2.77
     LIVE
    2.65
    live
    2.27
     live
    2.19
     Lives
    1.40
     Living
    1.25
     Alive
    1.20
     Offline
    1.13
     Stand
    1.08
    Activations Density 0.007%

    No Known Activations