© 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. 1-RES-JB
    6. 5344
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to business ventures or investments

    oai_token-act-pair · gpt-3.5-turbo

    references to companies and organizations, particularly in a business context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ezvous
    -0.84
    CAST
    -0.73
    ¯¯¯¯¯¯¯¯
    -0.72
    ãĤ´
    -0.72
     Stellar
    -0.67
     Pik
    -0.66
     grap
    -0.66
    sonian
    -0.65
     Io
    -0.65
    board
    -0.65
    POSITIVE LOGITS
    conservancy
    0.82
    mere
    0.78
    uchin
    0.76
     Oaks
    0.76
    ortex
    0.73
    bush
    0.69
    aido
    0.69
    abin
    0.68
     fold
    0.68
     valley
    0.67
    Activations Density 0.032%

    No Known Activations