© 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. 11-RES-JB
    11. 20505
    Prev
    Next
    INDEX
    Explanations

    information about a person's family and relationships after their passing

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate surviving family members and their relationships

    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
    imo
    -0.73
    Platform
    -0.72
    question
    -0.70
    generated
    -0.67
    anything
    -0.66
    æ©Ł
    -0.66
    cham
    -0.66
    ãĤ¨ãĥ«
    -0.66
    UGC
    -0.66
    direction
    -0.65
    POSITIVE LOGITS
     relatives
    1.51
     his
    1.40
     friends
    1.39
     cousins
    1.33
     wife
    1.32
     siblings
    1.28
     girlfriend
    1.27
     family
    1.23
     fiance
    1.23
     grandparents
    1.20
    Activations Density 0.374%

    No Known Activations