Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 11-RES-JB
    6. 15057
    Prev
    Next
    INDEX
    Explanations

    expressions related to love, caring, and family relationships

    oai_token-act-pair · gpt-3.5-turbo

    expressions of genuine friendship and emotional connections

    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
    •layer 11 - love

    No Comments

    Negative Logits
    milo
    -0.85
    EStream
    -0.81
    uscript
    -0.74
    UGC
    -0.72
    çīĪ
    -0.70
    ãĥķãĤ©
    -0.70
     counterfe
    -0.70
     typo
    -0.68
     Manufact
    -0.68
     heresy
    -0.67
    POSITIVE LOGITS
     caring
    1.36
     caregivers
    1.27
     kindness
    1.25
     cared
    1.24
     careg
    1.24
     affection
    1.23
     nurturing
    1.23
     uncond
    1.17
     warmth
    1.17
     loving
    1.16
    Activations Density 0.630%

    No Known Activations