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. 8-RES-JB
    6. 21857
    Prev
    Next
    INDEX
    Explanations

    age indications expressed in a "number-year-old" format

    oai_token-act-pair · gpt-3.5-turbo

    numerical references to the ages of children

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     flush
    -0.65
     akin
    -0.64
    Dialogue
    -0.64
    ufficient
    -0.62
    urgy
    -0.61
    ausible
    -0.60
     torches
    -0.60
     lobb
    -0.59
    aturday
    -0.59
    achus
    -0.59
    POSITIVE LOGITS
     olds
    1.15
     ago
    0.88
     old
    0.80
    OLD
    0.78
    old
    0.76
     anniversary
    0.74
    olds
    0.72
    iversary
    0.71
     veteran
    0.67
     pregnant
    0.66
    Activations Density 0.047%

    No Known Activations