© 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. 3304
    Prev
    Next
    INDEX
    Explanations

    descriptions of the age of individuals

    oai_token-act-pair · gpt-3.5-turbo

    references to the ages and genders of children

    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
    osponsors
    -0.85
    headers
    -0.84
    docs
    -0.82
    tools
    -0.78
    SOURCE
    -0.77
    HOME
    -0.76
    TIME
    -0.76
    kefeller
    -0.76
    ËĪ
    -0.75
    ivery
    -0.75
    POSITIVE LOGITS
     boy
    1.38
     girl
    1.35
     daughter
    1.27
     boys
    1.18
     girls
    1.14
     son
    1.13
     granddaughter
    1.07
     grandson
    1.05
     niece
    1.02
     nephew
    1.01
    Activations Density 0.082%

    No Known Activations