© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 3160
    Prev
    Next
    INDEX
    Explanations

    terms related to the concept of a millennium

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the term "Millennium" and its related contexts

    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
    opath
    -0.82
    ophy
    -0.81
    kies
    -0.79
    anooga
    -0.74
    otomy
    -0.74
    ierrez
    -0.70
    aceae
    -0.70
    otom
    -0.70
     integ
    -0.69
    OLOG
    -0.69
    POSITIVE LOGITS
     Millennium
    0.98
    enary
    0.90
    enium
    0.78
     Falcon
    0.77
     Copyright
    0.76
    enaries
    0.74
    heim
    0.72
    ãĤ¼ãĤ¦ãĤ¹
    0.71
    Fal
    0.70
    stein
    0.69
    Activations Density 0.023%

    No Known Activations