© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 1-RES-JB
    11. 15859
    Prev
    Next
    INDEX
    Explanations

    years expressed as numerical values followed by the term "year-old"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of ages in years

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    otos
    -0.86
    pload
    -0.81
     cumbers
    -0.80
    anches
    -0.79
    İĭ
    -0.79
     regress
    -0.75
    ipher
    -0.74
    ettings
    -0.72
     adjoining
    -0.72
    ŃĶ
    -0.72
    POSITIVE LOGITS
    old
    0.81
    rums
    0.79
     Frenchman
    0.78
     Trafford
    0.77
     boy
    0.74
    foundland
    0.72
    timer
    0.72
    stones
    0.72
    enburg
    0.69
    olds
    0.69
    Activations Density 0.025%

    No Known Activations