© 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. 4-RES-JB
    11. 14468
    Prev
    Next
    INDEX
    Explanations

    scientific terms and acronyms related to biological pathways and processes

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of negative expressions or terms related to various biological mechanisms

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

    No Comments

    Negative Logits
    ulhu
    -0.87
     Polk
    -0.80
    essee
    -0.79
     Wiz
    -0.78
    ãģ®å®
    -0.75
     Stranger
    -0.73
     Jimmy
    -0.73
    Ĥª
    -0.71
     Vaughn
    -0.71
     Borders
    -0.70
    POSITIVE LOGITS
    induced
    1.31
    mediated
    1.28
    derived
    1.21
    containing
    1.18
    bearing
    1.15
    based
    1.13
    shaped
    1.12
    dependent
    1.09
    treated
    1.08
    specific
    1.06
    Activations Density 0.182%

    No Known Activations