© 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. 20679
    Prev
    Next
    INDEX
    Explanations

    phrases referring to specific objects or concepts

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "this."

    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
    osponsors
    -0.89
    emale
    -0.81
    ographies
    -0.81
    acers
    -0.79
    姫
    -0.78
    ARDS
    -0.77
    aneers
    -0.76
    tops
    -0.76
    rights
    -0.75
    tones
    -0.75
    POSITIVE LOGITS
     nifty
    1.08
     adorable
    1.06
     delightful
    1.05
     lovely
    1.04
     amazing
    0.99
     gorgeous
    0.98
     hilarious
    0.97
     incredible
    0.97
     enigmatic
    0.94
     wonderful
    0.93
    Activations Density 0.133%

    No Known Activations