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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & 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. 5-RES-JB
    6. 19820
    Prev
    Next
    INDEX
    Explanations

    phrases related to things being annoying or causing annoyance

    oai_token-act-pair · gpt-3.5-turbo

    instances of words related to annoyance or irritation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ardless
    -0.90
    ariat
    -0.87
    arnaev
    -0.87
    ining
    -0.86
    borg
    -0.82
    yss
    -0.81
    ined
    -0.78
    knit
    -0.77
    inition
    -0.76
    bard
    -0.76
    POSITIVE LOGITS
     nuisance
    1.07
     annoy
    0.97
     obnoxious
    0.94
     annoyance
    0.91
     annoying
    0.89
     inconven
    0.85
     irritating
    0.80
     pests
    0.79
     quirks
    0.73
     harass
    0.72
    Activations Density 0.043%

    No Known Activations