© 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. 10-RES-JB
    11. 1274
    Prev
    Next
    INDEX
    Explanations

    words related to author's comments or side notes

    oai_token-act-pair · gpt-3.5-turbo

    expressions related to personal experiences and reflections

    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
    glass
    -0.74
    chieve
    -0.64
    lot
    -0.59
     Reincarnated
    -0.59
    natureconservancy
    -0.59
     Everywhere
    -0.59
     Jobs
    -0.57
     reperto
    -0.57
    ãĥīãĥ©
    -0.56
    Newsletter
    -0.55
    POSITIVE LOGITS
     suffice
    1.21
     spoiler
    1.13
     summarize
    1.12
     summar
    1.00
     briefly
    0.99
     Spoiler
    0.95
    Disclaimer
    0.95
     disclaimer
    0.92
     omit
    0.92
     skip
    0.90
    Activations Density 0.345%

    No Known Activations