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

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 8-RES-JB
    6. 22137
    Prev
    Next
    INDEX
    Explanations

    phrases related to feeling inspired or being a source of inspiration

    oai_token-act-pair · gpt-3.5-turbo

    terms related to inspiration and motivation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    til
    -0.73
    minster
    -0.69
    ntil
    -0.68
    talk
    -0.67
    estation
    -0.67
    ophon
    -0.67
    eln
    -0.66
    alon
    -0.66
    othe
    -0.66
     Canad
    -0.65
    POSITIVE LOGITS
    iration
    1.17
     inspiration
    1.03
     Cosponsors
    1.00
     inspiring
    0.88
     muse
    0.85
     Inspired
    0.71
    andise
    0.71
     awe
    0.71
     artwork
    0.70
     quotes
    0.70
    Activations Density 0.067%

    No Known Activations