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. 2-RES-JB
    6. 8736
    Prev
    Next
    INDEX
    Explanations

    mentions or references to RSS feeds

    oai_token-act-pair · gpt-3.5-turbo

    references to RSS feeds and subscriptions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Hurricanes
    -0.86
    esville
    -0.86
    eu
    -0.76
    È
    -0.75
    gran
    -0.74
    ortium
    -0.70
    empl
    -0.69
    orneys
    -0.69
     Kardashian
    -0.67
    cellence
    -0.67
    POSITIVE LOGITS
     RSS
    1.16
     feeds
    1.01
     mosqu
    0.99
    rss
    0.91
     feed
    0.89
     guiActiveUn
    0.88
     Aure
    0.83
     Feed
    0.81
     subscriptions
    0.73
     undermin
    0.73
    Activations Density 0.007%

    No Known Activations