© 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. 17835
    Prev
    Next
    INDEX
    Explanations

    instances of the word "quick to" followed by an action

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "to" in various contexts

    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
    soDeliveryDate
    -0.81
    Offline
    -0.80
     Continued
    -0.69
     Compass
    -0.68
    Lear
    -0.66
    soever
    -0.65
     Tsukuyomi
    -0.64
     Kinnikuman
    -0.63
    OTAL
    -0.63
     Cups
    -0.62
    POSITIVE LOGITS
     criticize
    1.32
     congratulate
    1.26
     remind
    1.25
     emphasize
    1.22
     reassure
    1.21
     announce
    1.21
     acknowledge
    1.20
     denounce
    1.19
     declare
    1.16
     endorse
    1.16
    Activations Density 0.231%

    No Known Activations