© 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. 11-RES-JB
    11. 14979
    Prev
    Next
    INDEX
    Explanations

    people's ages and age ranges

    oai_token-act-pair · gpt-3.5-turbo

    age ranges in a demographic context

    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
     Dres
    -0.64
     dh
    -0.62
     bark
    -0.58
     Artemis
    -0.58
    anz
    -0.58
     scal
    -0.57
     Sap
    -0.56
     Helpful
    -0.56
    EStreamFrame
    -0.55
     antib
    -0.55
    POSITIVE LOGITS
    49
    0.92
     49
    0.88
    34
    0.86
     34
    0.86
     64
    0.83
    24
    0.83
     29
    0.82
     65
    0.82
     44
    0.82
     Older
    0.80
    Activations Density 0.039%

    No Known Activations