© 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. 8-RES-JB
    11. 17603
    Prev
    Next
    INDEX
    Explanations

    instances where an object or item is being described with an emphasis on its specific features

    oai_token-act-pair · gpt-3.5-turbo

    references to relationships or connections in phrases

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ONE
    -0.73
     Thoughts
    -0.70
     Planning
    -0.66
     wounding
    -0.64
    ODY
    -0.64
     Hunting
    -0.60
    KNOWN
    -0.59
     Corpus
    -0.58
    Eye
    -0.58
     Equity
    -0.58
    POSITIVE LOGITS
     resembles
    1.22
     extends
    1.17
     accompanies
    1.14
     protects
    1.08
     spans
    1.08
     corresponds
    1.08
     regulates
    1.06
     allows
    1.05
     enables
    1.04
     includes
    1.03
    Activations Density 0.186%

    No Known Activations