© 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 EvalsExportsinterp-engineNEWAPI 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. 11-RES-JB
    11. 21193
    Prev
    Next
    INDEX
    Explanations

    age ranges of people

    oai_token-act-pair · gpt-3.5-turbo

    demographic information related to age groups in surveys

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    atl
    -0.73
    asus
    -0.63
    natureconservancy
    -0.63
     accord
    -0.60
    itsch
    -0.60
     Trin
    -0.60
     racket
    -0.59
     Basil
    -0.59
    alog
    -0.58
    artifacts
    -0.57
    POSITIVE LOGITS
    +.
    1.17
    +,
    1.13
    +)
    1.11
     ages
    0.96
    yrs
    0.95
    years
    0.92
     years
    0.92
     age
    0.91
    +
    0.82
    yo
    0.78
    Activations Density 0.085%

    No Known Activations