© 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. 2-RES-JB
    11. 5354
    Prev
    Next
    INDEX
    Explanations

    phrases related to possession or ownership

    oai_token-act-pair · gpt-3.5-turbo

    the preposition "of" and related phrases indicating possession or association

    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
     partName
    -0.75
    ashtra
    -0.68
     Cosponsors
    -0.67
    culosis
    -0.62
    pots
    -0.60
     reperto
    -0.59
     showc
    -0.58
     ende
    -0.58
    helle
    -0.57
     istg
    -0.56
    POSITIVE LOGITS
     course
    1.11
     sorts
    0.99
    icial
    0.84
    course
    0.84
     ours
    0.79
     theirs
    0.73
     hers
    0.64
     the
    0.61
     those
    0.60
     Course
    0.59
    Activations Density 1.132%

    No Known Activations