© 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. 0-RES-JB
    11. 13771
    Prev
    Next
    INDEX
    Explanations

    terms related to documents or files

    oai_token-act-pair · gpt-3.5-turbo

    references to documents and document-related terminology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     tails
    -0.78
     equilibrium
    -0.75
    phia
    -0.74
     decay
    -0.73
    ococ
    -0.72
     beta
    -0.72
     energies
    -0.71
    anka
    -0.70
     ratios
    -0.70
     rush
    -0.68
    POSITIVE LOGITS
    Document
    3.06
     Document
    3.03
    document
    2.50
    ocument
    1.67
    DOM
    1.40
    ument
    1.39
     DOC
    1.35
     Dram
    1.26
     DOM
    1.25
     Documentation
    1.22
    Activations Density 0.036%

    No Known Activations