© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 3-RES-JB
    11. 1868
    Prev
    Next
    INDEX
    Explanations

    phrases related to overseeing or supervising tasks or projects

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "oversee" and its variants, indicating oversight and management roles

    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
    seed
    -0.68
    bite
    -0.65
    Secondly
    -0.65
    bag
    -0.65
    ening
    -0.63
    ا
    -0.62
    False
    -0.62
    plane
    -0.61
    Spoiler
    -0.61
     Tac
    -0.61
    POSITIVE LOGITS
     overseeing
    1.25
     overseen
    1.08
     oversee
    1.03
     oversaw
    0.91
     oversees
    0.84
    orship
    0.82
     superv
    0.77
    İĭ
    0.77
     presided
    0.77
    ership
    0.74
    Activations Density 0.022%

    No Known Activations