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. 3-RES-JB
    6. 11696
    Prev
    Next
    INDEX
    Explanations

    mentions of "**ub**" in the context of a username, likely related to online platforms

    oai_token-act-pair · gpt-3.5-turbo

    instances of the substring 'ub'

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Lauder
    -0.75
     ozone
    -0.72
     ORIG
    -0.66
     cig
    -0.65
     Noir
    -0.64
     Sagan
    -0.64
     Virgin
    -0.62
    chnology
    -0.61
     Glac
    -0.61
     Atlantic
    -0.60
    POSITIVE LOGITS
    bing
    1.30
    lishing
    1.29
    lish
    1.21
    lisher
    1.15
    bed
    1.15
    rious
    1.14
    bish
    1.14
    bers
    1.07
    lique
    1.05
    bies
    1.00
    Activations Density 0.012%

    No Known Activations