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. 5-RES-JB
    6. 20613
    Prev
    Next
    INDEX
    Explanations

    phrases that are commonly found at the end of advertisements

    oai_token-act-pair · gpt-3.5-turbo

    recurring phrases related to advertisement placement in articles

    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
    bags
    -0.75
    bag
    -0.70
    MM
    -0.67
    issance
    -0.66
    è¦ļéĨĴ
    -0.66
    axe
    -0.64
    RAW
    -0.62
     Gujar
    -0.62
    Writ
    -0.62
    ointed
    -0.60
    POSITIVE LOGITS
     Thumbnails
    0.74
    ideshow
    0.73
     trending
    0.71
    imeo
    0.70
     Loading
    0.65
    oulos
    0.61
     slideshow
    0.61
    lando
    0.60
    deck
    0.60
     slide
    0.59
    Activations Density 0.016%

    No Known Activations