© 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. 10-RES-JB
    11. 6430
    Prev
    Next
    INDEX
    Explanations

    expressions related to emotional support, care, and companionship

    oai_token-act-pair · gpt-3.5-turbo

    expressions of love, support, and emotional connection

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     inacc
    -0.97
     typo
    -0.79
     captcha
    -0.78
     inaccurate
    -0.75
     piracy
    -0.74
     incendiary
    -0.72
     Gutenberg
    -0.72
     disinformation
    -0.72
     inference
    -0.71
     acron
    -0.69
    POSITIVE LOGITS
     loving
    1.41
     caring
    1.36
     loved
    1.36
     cared
    1.34
     uncond
    1.29
     nurture
    1.23
     affection
    1.22
     nurturing
    1.21
     careg
    1.19
     caregivers
    1.19
    Activations Density 0.514%

    No Known Activations