© 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. 2-RES-JB
    11. 23839
    Prev
    Next
    INDEX
    Explanations

    words related to gratitude, service, and compassion

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to compassion and support for vulnerable populations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    pload
    -0.64
     Reported
    -0.63
    OVA
    -0.61
     rack
    -0.60
    urst
    -0.59
     Presumably
    -0.59
     guiActiveUn
    -0.57
    ãĥĥãĥĪ
    -0.56
    iquid
    -0.56
    tail
    -0.56
    POSITIVE LOGITS
     compassion
    0.77
     dignity
    0.76
     compassionate
    0.75
     courageous
    0.73
    natureconservancy
    0.70
     sacrific
    0.69
     Dialogue
    0.69
     caring
    0.68
     patri
    0.68
     vigil
    0.68
    Activations Density 2.922%

    No Known Activations