© 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. 5492
    Prev
    Next
    INDEX
    Explanations

    mentions of objects or individuals that are rounded or the act of rounding up individuals

    oai_token-act-pair · gpt-3.5-turbo

    words related to the concept of being rounded or curvilinear forms

    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
    ettel
    -0.71
    natureconservancy
    -0.66
    adder
    -0.63
    href
    -0.62
    alogy
    -0.61
    andum
    -0.61
    inese
    -0.60
     appropriation
    -0.60
    orship
    -0.60
    idence
    -0.58
    POSITIVE LOGITS
     rounded
    0.98
    abouts
    0.94
     rounding
    0.90
     corners
    0.85
     Seym
    0.84
    uled
    0.79
    rounded
    0.77
     Ambro
    0.69
    Split
    0.68
    Disclaimer
    0.67
    Activations Density 0.010%

    No Known Activations