© 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. 20518
    Prev
    Next
    INDEX
    Explanations

    prepositions and verbs related to actions or initiatives

    oai_token-act-pair · gpt-3.5-turbo

    specific historical events and terms related to memory and documentation

    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
     Bok
    -0.80
     Jong
    -0.80
     Karma
    -0.75
     Blues
    -0.74
     Haku
    -0.74
     Snap
    -0.73
    balls
    -0.73
    yang
    -0.71
     Buk
    -0.71
    alin
    -0.71
    POSITIVE LOGITS
    ĸļ士
    0.98
    Orderable
    0.95
    DeliveryDate
    0.92
    phys
    0.91
    NetMessage
    0.88
    uyomi
    0.87
     Ecc
    0.85
    ennes
    0.84
    Phill
    0.84
    VIDIA
    0.83
    Activations Density 0.440%

    No Known Activations