© 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. 14247
    Prev
    Next
    INDEX
    Explanations

    references to individuals who have retired

    oai_token-act-pair · gpt-3.5-turbo

    the mention of individuals who are retired from various professions

    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
    ellen
    -0.68
    gs
    -0.67
     Grimm
    -0.67
    matic
    -0.66
    maps
    -0.66
    bring
    -0.66
    aug
    -0.66
    NG
    -0.65
    WAY
    -0.64
    ñ
    -0.64
    POSITIVE LOGITS
     retired
    1.21
     retiring
    1.17
     retire
    0.99
     retirees
    0.86
     retirement
    0.83
    dinand
    0.80
     veter
    0.76
     pensions
    0.73
    lyak
    0.72
    ired
    0.72
    Activations Density 0.006%

    No Known Activations