© 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. 17657
    Prev
    Next
    INDEX
    Explanations

    phrases describing someone or something as exceptional in a particular field

    oai_token-act-pair · gpt-3.5-turbo

    instances of the phrase "in" with varying contexts suggesting significance or notable characteristics

    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
    DragonMagazine
    -0.75
    Query
    -0.74
    612
    -0.66
    659
    -0.66
     Cosponsors
    -0.64
    642
    -0.63
    263
    -0.61
    oother
    -0.61
    649
    -0.60
    ãĤ³
    -0.60
    POSITIVE LOGITS
     existence
    1.16
     terms
    1.02
     history
    0.97
    efficiency
    0.96
    clusions
    0.93
     America
    0.87
    ducers
    0.87
     Europe
    0.86
    herent
    0.85
    effic
    0.83
    Activations Density 0.109%

    No Known Activations