© 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. 11-RES-JB
    11. 21613
    Prev
    Next
    INDEX
    Explanations

    phrases related to varied topics such as technology, job-seeking advice, personal emotions, movie titles, and more

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating skepticism or caution

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     tremend
    -1.20
     carbohyd
    -1.10
     referen
    -1.08
     periphery
    -1.05
     regress
    -1.04
     eleph
    -1.03
     pressures
    -1.03
     satell
    -1.02
     arming
    -1.01
     parity
    -1.00
    POSITIVE LOGITS
     Place
    1.39
     Relationship
    1.39
     Thing
    1.39
     Stuff
    1.33
     Favorite
    1.33
     Own
    1.32
     Month
    1.30
     Dating
    1.30
     Conversation
    1.29
     Difference
    1.28
    Activations Density 0.268%

    No Known Activations