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. 3-RES-JB
    6. 11057
    Prev
    Next
    INDEX
    Explanations

    words related to aging

    oai_token-act-pair · gpt-3.5-turbo

    words related to aging or processes that involve gradual decline

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    kefeller
    -0.70
     Mub
    -0.65
    æ©Ł
    -0.64
    ihar
    -0.63
    merce
    -0.62
     sidel
    -0.62
     Bean
    -0.61
    fitting
    -0.61
     manif
    -0.60
     suited
    -0.59
    POSITIVE LOGITS
    hog
    1.16
    ged
    0.90
    ges
    0.89
    rets
    0.84
    gers
    0.83
    ging
    0.79
    orge
    0.76
    geoning
    0.75
    tons
    0.72
    oliath
    0.72
    Activations Density 0.015%

    No Known Activations