© 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. 1-RES-JB
    11. 3904
    Prev
    Next
    INDEX
    Explanations

    words related to desalination

    oai_token-act-pair · gpt-3.5-turbo

    terms related to the concept of "domination" or "subordination."

    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
    arers
    -0.71
     substantial
    -0.63
    published
    -0.61
     behalf
    -0.61
     Canadians
    -0.58
     dramatic
    -0.57
     modest
    -0.56
    herty
    -0.56
    ãģį
    -0.56
     immediate
    -0.55
    POSITIVE LOGITS
    ination
    1.34
    rontal
    0.95
    hower
    0.88
    itial
    0.83
    inations
    0.83
    terness
    0.80
    icol
    0.78
    naire
    0.78
    spection
    0.77
    eering
    0.75
    Activations Density 0.007%

    No Known Activations