© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 19755
    Prev
    Next
    INDEX
    Explanations

    positive words or sentiments

    oai_token-act-pair · gpt-3.5-turbo

    expressions of positive sentiment

    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
     spo
    -0.65
     Brilliant
    -0.63
     sidel
    -0.57
     stride
    -0.56
     Recall
    -0.56
     crest
    -0.55
     Lucia
    -0.54
    ways
    -0.54
     Chancellor
    -0.54
     Boko
    -0.53
    POSITIVE LOGITS
    itional
    1.75
    itions
    1.66
    itivity
    1.50
    itionally
    1.41
    itives
    1.37
    icion
    1.37
    itiveness
    1.34
    ession
    1.28
    itive
    1.28
    essed
    1.28
    Activations Density 0.055%

    No Known Activations