© 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. 9-RES-JB
    11. 10039
    Prev
    Next
    INDEX
    Explanations

    specific years, tech-related terms, and software or app names

    oai_token-act-pair · gpt-3.5-turbo

    references to apps and technology updates

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Dialogue
    -0.74
     Dialogue
    -0.67
    tsky
    -0.66
     narratives
    -0.66
     Correspond
    -0.66
     extremes
    -0.65
     Taxes
    -0.63
     Gerry
    -0.62
     reconc
    -0.62
     speeches
    -0.62
    POSITIVE LOGITS
     installed
    1.14
     marketed
    1.12
     commercially
    1.05
     debuted
    1.04
     discontinued
    1.02
    installed
    1.00
     implemented
    0.97
     deployed
    0.96
     rollout
    0.95
    available
    0.95
    Activations Density 0.549%

    No Known Activations