© 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. 7-RES-JB
    11. 8967
    Prev
    Next
    INDEX
    Explanations

    phrases related to technology and innovation

    oai_token-act-pair · gpt-3.5-turbo

    references to systems of responsibility, particularly in civic, health, and governmental contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     pse
    -0.86
     maybe
    -0.80
     plaus
    -0.73
     mang
    -0.73
     idiot
    -0.73
     kinda
    -0.72
     sucker
    -0.72
     sideways
    -0.72
     stupid
    -0.71
     Stupid
    -0.71
    POSITIVE LOGITS
    ###
    1.03
    Through
    1.00
    Learn
    0.97
    Additionally
    0.97
    Companies
    0.97
    ONSORED
    0.96
    quartered
    0.95
    Laun
    0.94
    Products
    0.94
    enture
    0.93
    Activations Density 0.689%

    No Known Activations