© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 11-RES-JB
    6. 1816
    Prev
    Next
    INDEX
    Explanations

    mentions of specific centers or locations, possibly related to events happening there

    oai_token-act-pair · gpt-3.5-turbo

    references to specific locations and institutions

    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
    wagen
    -0.76
     Ja
    -0.76
     Stev
    -0.75
     Subaru
    -0.74
     whisky
    -0.73
    azo
    -0.73
    prop
    -0.72
     rigged
    -0.72
     tob
    -0.71
     synt
    -0.70
    POSITIVE LOGITS
     center
    1.90
    Cent
    1.88
    center
    1.85
     CENT
    1.84
     Cent
    1.82
    Center
    1.82
     Center
    1.78
     centers
    1.67
     centre
    1.62
    CENT
    1.60
    Activations Density 0.222%

    No Known Activations