© 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. 9-RES-JB
    11. 8592
    Prev
    Next
    INDEX
    Explanations

    phrases related to relationships and marriages

    oai_token-act-pair · gpt-3.5-turbo

    narratives of enduring friendships and relationships from childhood

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    herer
    -0.76
    earchers
    -0.72
    ribune
    -0.70
    ateurs
    -0.69
    odder
    -0.69
    arcity
    -0.68
    jriwal
    -0.68
    araoh
    -0.67
    govtrack
    -0.66
    umper
    -0.65
    POSITIVE LOGITS
     friendship
    1.40
     mutual
    1.30
     mutually
    1.28
     Together
    1.17
     together
    1.14
     relationship
    1.12
     intimacy
    1.12
    relations
    1.11
    Relations
    1.11
    together
    1.07
    Activations Density 1.318%

    No Known Activations