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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 11-RES-JB
    11. 781
    Prev
    Next
    INDEX
    Explanations

    mentions of liquid droplets or medical drops

    oai_token-act-pair · gpt-3.5-turbo

    variations of the word "drop" and its related forms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Triangle
    -0.65
     Trident
    -0.64
     amd
    -0.61
     mirrors
    -0.61
     Canary
    -0.59
     Swordsman
    -0.58
     reconciliation
    -0.58
     CVE
    -0.58
    shire
    -0.58
     à¨
    -0.56
    POSITIVE LOGITS
    plets
    1.64
    ppings
    1.54
    plet
    1.49
    ppers
    1.40
    oling
    1.34
    ves
    1.31
    pper
    1.30
    oping
    1.22
    pping
    1.21
    pped
    1.18
    Activations Density 0.024%

    No Known Activations