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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & 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. 20806
    Prev
    Next
    INDEX
    Explanations

    mentions of the term "Insiders" followed by a number, potentially related to various contexts such as sports, business, or politics

    oai_token-act-pair · gpt-3.5-turbo

    references to an organization or entity abbreviated as "Ins."

    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
    âĢ¢âĢ¢
    -0.76
    ãĥ£
    -0.75
    theless
    -0.73
     litter
    -0.68
    ries
    -0.68
    WARE
    -0.66
    DragonMagazine
    -0.66
    çĦ
    -0.65
     Mata
    -0.63
    EStream
    -0.62
    POSITIVE LOGITS
    ufficient
    1.10
    ights
    1.08
    urrection
    1.07
    urance
    1.05
    iders
    1.03
    omnia
    0.99
    urg
    0.96
    idious
    0.96
    ider
    0.89
    pect
    0.89
    Activations Density 0.013%

    No Known Activations