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. 10-RES-JB
    6. 24118
    Prev
    Next
    INDEX
    Explanations

    phrases related to email subscriptions and website upgrades

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to personal customization and interaction with digital content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    :[
    -0.60
    forth
    -0.58
     Lump
    -0.57
     Bord
    -0.55
    peak
    -0.54
    opol
    -0.54
    hunt
    -0.54
     Caucasian
    -0.53
     explan
    -0.53
     excluding
    -0.52
    POSITIVE LOGITS
     inbox
    0.80
    ģ«
    0.66
     html
    0.61
     subscription
    0.60
    ecast
    0.60
     guiActive
    0.60
    rimp
    0.59
    edia
    0.58
     browser
    0.58
    iku
    0.58
    Activations Density 0.026%

    No Known Activations