© 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. 9946
    Prev
    Next
    INDEX
    Explanations

    references to caring for and expressing love towards someone

    oai_token-act-pair · gpt-3.5-turbo

    references to a specific female subject and her relationship with others

    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
    •layer 9 - love

    No Comments

    Negative Logits
    ACP
    -0.89
    arios
    -0.73
    irm
    -0.73
    ocument
    -0.68
    ãĥĩãĤ£
    -0.67
    scrib
    -0.66
    ffic
    -0.63
    omination
    -0.62
     Hasan
    -0.60
    adobe
    -0.60
    POSITIVE LOGITS
     Majesty
    1.13
     POV
    0.94
     majesty
    0.91
     psyche
    0.73
    âĹ¼
    0.67
     backstory
    0.62
     reluct
    0.60
     motivation
    0.59
    iets
    0.59
     psychology
    0.57
    Activations Density 0.303%

    No Known Activations