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. 2-RES-JB
    6. 20499
    Prev
    Next
    INDEX
    Explanations

    phrases related to the age of individuals, particularly using the term "olds"

    oai_token-act-pair · gpt-3.5-turbo

    references to age groups or the term "olds."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    SOURCE
    -0.69
    yss
    -0.65
    ophys
    -0.64
     ethics
    -0.63
    onyms
    -0.62
     arbit
    -0.60
     constitu
    -0.59
     NX
    -0.58
     adjunct
    -0.58
     EMS
    -0.58
    POSITIVE LOGITS
    chool
    1.12
    olds
    0.98
    pring
    0.98
    warm
    0.92
    hips
    0.89
    velt
    0.88
    aurus
    0.83
    mith
    0.82
    hack
    0.79
    erers
    0.79
    Activations Density 0.016%

    No Known Activations