© 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. 6744
    Prev
    Next
    INDEX
    Explanations

    phrases related to being full of something or containing something

    oai_token-act-pair · gpt-3.5-turbo

    phrases containing the word "with" and its associations

    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
    wake
    -0.82
    NPR
    -0.75
    Commission
    -0.75
    mia
    -0.73
    Enlarge
    -0.70
    DragonMagazine
    -0.69
    BN
    -0.69
    starting
    -0.68
    wk
    -0.68
    mie
    -0.68
    POSITIVE LOGITS
     surprises
    1.22
     contradictions
    1.16
     goodies
    1.12
     intrigue
    1.03
     symbolism
    0.97
     acron
    0.96
     jewels
    0.92
     possibilities
    0.91
     mysteries
    0.91
     riches
    0.91
    Activations Density 0.117%

    No Known Activations