© 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. 0-RES-JB
    11. 11525
    Prev
    Next
    INDEX
    Explanations

    references to the millennial generation

    oai_token-act-pair · gpt-3.5-turbo

    terms related to the Millennial generation

    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
     referee
    -0.71
     sham
    -0.69
    endar
    -0.68
    ieu
    -0.68
     triangle
    -0.68
    inho
    -0.66
    ja
    -0.66
     scripting
    -0.65
    quished
    -0.65
     ballet
    -0.65
    POSITIVE LOGITS
     Millenn
    3.22
     Millennials
    2.87
    Mill
    2.38
     millennials
    1.73
     millennial
    1.60
     Generations
    1.30
    venth
    1.23
     twent
    1.17
     Millennium
    0.96
    fol
    0.95
    Activations Density 0.027%

    No Known Activations