© 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. 20297
    Prev
    Next
    INDEX
    Explanations

    acronyms starting with "NC" followed by a single digit

    oai_token-act-pair · gpt-3.5-turbo

    repeated references to the acronym "NC," likely related to specific organizations or terms in a context that involves legal, medical, or organizational topics

    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
    chest
    -0.83
    ãĤ¯
    -0.66
    ~~~~
    -0.66
    hab
    -0.65
    thing
    -0.65
    dog
    -0.64
    mir
    -0.64
    ~~~~~~~~~~~~~~~~
    -0.64
    ãĥĦ
    -0.63
    _____
    -0.63
    POSITIVE LOGITS
    NC
    1.20
     NC
    0.91
    ODE
    0.90
    ATH
    0.88
    urrent
    0.87
    urses
    0.83
    ossus
    0.83
    ADE
    0.79
    amera
    0.78
    CLASSIFIED
    0.76
    Activations Density 0.006%

    No Known Activations