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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 4-RES-JB
    6. 8056
    Prev
    Next
    INDEX
    Explanations

    advertisements and content related to signing up for newsletters or sharing stories online

    oai_token-act-pair · gpt-3.5-turbo

    calls to action related to subscribing or signing up for a newsletter

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

    No Comments

    Negative Logits
    itone
    -0.37
    omorphic
    -0.37
    worldly
    -0.34
    Ĥª
    -0.34
     sentient
    -0.33
     embodiments
    -0.33
     cabinets
    -0.32
    wagen
    -0.32
    antle
    -0.32
     dracon
    -0.32
    POSITIVE LOGITS
    news
    0.42
    embed
    0.41
    iframe
    0.41
     UNCLASSIFIED
    0.41
    img
    0.41
    gallery
    0.40
    biz
    0.39
     Tribune
    0.39
    email
    0.39
     embed
    0.38
    Activations Density 0.779%

    No Known Activations