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. 8-RES-JB
    6. 20558
    Prev
    Next
    INDEX
    Explanations

    phrases related to excitement and anticipation

    oai_token-act-pair · gpt-3.5-turbo

    expressions of anticipation or excitement related to upcoming events or experiences

    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
    itored
    -0.71
    ureau
    -0.68
    angering
    -0.66
    nown
    -0.65
    administ
    -0.64
    licted
    -0.63
     administ
    -0.63
    earcher
    -0.62
     administr
    -0.62
    anwhile
    -0.61
    POSITIVE LOGITS
     indie
    0.82
     pics
    0.78
     Vinyl
    0.77
     Xperia
    0.75
     albums
    0.74
     themed
    0.74
     adorable
    0.73
     anime
    0.73
     Halloween
    0.72
     gorgeous
    0.72
    Activations Density 1.251%

    No Known Activations