© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 7-RES-JB
    6. 10009
    Prev
    Next
    INDEX
    Explanations

    names and actions related to personal interactions and relationships

    oai_token-act-pair · gpt-3.5-turbo

    elements of personal relationships and their dynamics

    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
     rall
    -0.68
    Sax
    -0.66
    raltar
    -0.64
    enhagen
    -0.64
    ÃĥÃĤ
    -0.63
    solete
    -0.63
    uay
    -0.62
    udo
    -0.62
     SDL
    -0.62
    espie
    -0.61
    POSITIVE LOGITS
     herself
    1.96
     husband
    1.18
     childbirth
    1.04
     boyfriend
    1.03
     pregnant
    1.02
     maid
    1.02
     breasts
    1.00
     maiden
    0.95
     menstru
    0.95
     breastfeeding
    0.94
    Activations Density 1.262%

    No Known Activations