Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 10-RES-JB
    6. 20746
    Prev
    Next
    INDEX
    Explanations

    phrases related to the duration of time someone has spent in a particular job or position

    oai_token-act-pair · gpt-3.5-turbo

    mentions of duration, particularly in terms of years or decades

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rium
    -0.75
    idden
    -0.66
    morrow
    -0.63
    esson
    -0.63
    react
    -0.62
    ussed
    -0.61
    eus
    -0.59
    atered
    -0.58
     Torch
    -0.57
    asma
    -0.56
    POSITIVE LOGITS
     ago
    1.00
     stint
    0.96
     spanning
    0.91
     specializing
    0.84
     earning
    0.80
     volunteering
    0.78
     retiring
    0.76
     consecut
    0.75
     uninterrupted
    0.74
     unbeaten
    0.72
    Activations Density 0.101%

    No Known Activations