© 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. 9480
    Prev
    Next
    INDEX
    Explanations

    phrases related to professional services or discussions

    oai_token-act-pair · gpt-3.5-turbo

    periods and punctuation marks indicating the end of thoughts or statements

    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
     grop
    -0.96
     pse
    -0.91
     undecided
    -0.79
     tape
    -0.79
     presumably
    -0.78
     sucker
    -0.76
    xual
    -0.76
     mating
    -0.75
     territorial
    -0.73
     neighb
    -0.72
    POSITIVE LOGITS
    Learn
    1.54
    Discover
    1.44
    Features
    1.44
    Join
    1.39
    Supported
    1.37
    Spons
    1.32
    Explore
    1.30
    Contact
    1.30
    Our
    1.29
    Featured
    1.29
    Activations Density 0.378%

    No Known Activations