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

    Neuronpedia

    Jacobian LensNEW
    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. 10-RES-JB
    11. 16522
    Prev
    Next
    INDEX
    Explanations

    phrases indicating a comparison of different qualities or attributes

    oai_token-act-pair · gpt-3.5-turbo

    descriptive phrases that indicate the quality or condition of something

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Footnote
    -0.64
    achment
    -0.60
    ench
    -0.55
     âĻ
    -0.54
    ppa
    -0.54
     Goddess
    -0.54
     refresh
    -0.53
    oire
    -0.52
     pump
    -0.52
     Ago
    -0.51
    POSITIVE LOGITS
     termed
    1.14
     arguably
    1.05
     essentially
    1.01
     billed
    0.99
     ordinarily
    0.97
     rightfully
    0.93
     otherwise
    0.90
     aptly
    0.90
     euphem
    0.88
     undoubtedly
    0.88
    Activations Density 0.058%

    No Known Activations