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

    Neuronpedia

    Jacobian LensNEW
    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. 7-RES-JB
    11. 21229
    Prev
    Next
    INDEX
    Explanations

    ages and specific ages (e.g., "thirteen", "twenty")

    oai_token-act-pair · gpt-3.5-turbo

    references to age, specifically the phrase "was X years old."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    sonian
    -0.85
     largeDownload
    -0.70
    lly
    -0.68
    ological
    -0.65
    oreal
    -0.64
    osate
    -0.64
    icular
    -0.63
    letal
    -0.63
    ertodd
    -0.63
    do
    -0.63
    POSITIVE LOGITS
     able
    0.83
     confronted
    0.79
     planning
    0.79
     weakest
    0.78
     supposed
    0.77
     touring
    0.77
     nearing
    0.77
     browsing
    0.75
     gearing
    0.74
     seated
    0.74
    Activations Density 0.125%

    No Known Activations