© 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. 7448
    Prev
    Next
    INDEX
    Explanations

    personal relationships and emotions

    oai_token-act-pair · gpt-3.5-turbo

    references to relationships and emotions associated with love and attachment

    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
     transpired
    -0.65
     QUEST
    -0.61
    Assembly
    -0.61
     Americas
    -0.59
    uthor
    -0.57
    ribe
    -0.56
    assembly
    -0.56
     Carbon
    -0.56
    äºĶ
    -0.55
    Explore
    -0.54
    POSITIVE LOGITS
     dearly
    1.51
     uncond
    1.34
     immensely
    1.00
     passionately
    0.89
     sacrific
    0.87
     enough
    0.85
     sincerely
    0.84
     enormously
    0.84
     greatly
    0.83
     tremendously
    0.83
    Activations Density 0.263%

    No Known Activations