© 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. 7-RES-JB
    11. 2118
    Prev
    Next
    INDEX
    Explanations

    phrases related to emotions and communication

    oai_token-act-pair · gpt-3.5-turbo

    emotional expressions related to performance or personal struggles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    espie
    -0.87
     helicop
    -0.83
     stewards
    -0.83
     Carson
    -0.82
    Colorado
    -0.81
     FedEx
    -0.80
     Colorado
    -0.79
     Webb
    -0.79
     bolted
    -0.78
     Buchanan
    -0.78
    POSITIVE LOGITS
    ãĢİ
    1.32
    ãĢIJ
    1.30
     manga
    1.29
     ãĢĮ
    1.28
    ãĢ
    1.21
     anime
    1.21
     Yamato
    1.20
     Anime
    1.18
     æ
    1.17
    âĺĨ
    1.16
    Activations Density 0.798%

    No Known Activations