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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 11-RES-JB
    6. 4264
    Prev
    Next
    INDEX
    Explanations

    ages and age-related information

    oai_token-act-pair · gpt-3.5-turbo

    phrases and terms related to age groups

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    hyde
    -0.94
     pandemonium
    -0.67
     havoc
    -0.66
    atl
    -0.63
     Word
    -0.63
    awan
    -0.61
     Papers
    -0.60
    assian
    -0.59
     Wast
    -0.59
     chalk
    -0.59
    POSITIVE LOGITS
     age
    1.29
     ages
    1.05
     65
    0.98
     eighteen
    0.98
     18
    0.98
     35
    0.90
    represented
    0.89
     25
    0.86
     Ages
    0.86
     30
    0.86
    Activations Density 0.070%

    No Known Activations