© 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. 11-RES-JB
    11. 923
    Prev
    Next
    INDEX
    Explanations

    instances of strong positive sentiment or emotion

    oai_token-act-pair · gpt-3.5-turbo

    intense expressions of feelings related to happiness and pride

    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
    Not in Any Lists

    No Comments

    Negative Logits
    Afee
    -0.63
     Days
    -0.62
    ŃĶ
    -0.60
     Thing
    -0.60
     Modes
    -0.58
    éŃĶ
    -0.58
     hegemony
    -0.58
     Curve
    -0.57
     viz
    -0.57
     Combine
    -0.57
    POSITIVE LOGITS
     thankful
    1.54
     grateful
    1.52
     pleased
    1.46
     glad
    1.42
     proud
    1.38
     saddened
    1.35
     excited
    1.34
     disappointed
    1.32
     sorry
    1.24
     thrilled
    1.24
    Activations Density 0.077%

    No Known Activations