© 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. 16032
    Prev
    Next
    INDEX
    Explanations

    positive reviews or comments about various things, such as shows, songs, books, food, and products

    oai_token-act-pair · gpt-3.5-turbo

    sentences that express strong positive opinions or enjoyments

    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
    anguage
    -0.77
    idal
    -0.76
     inference
    -0.71
     renegoti
    -0.70
     concess
    -0.70
     suspic
    -0.69
     casualty
    -0.69
     disadvantage
    -0.68
     forfeit
    -0.68
    ormal
    -0.66
    POSITIVE LOGITS
     Especially
    1.45
     Firstly
    1.41
     Featuring
    1.30
     Literally
    1.29
     Seriously
    1.26
     Its
    1.26
     Every
    1.20
     Particularly
    1.20
     Located
    1.17
     Sure
    1.16
    Activations Density 0.384%

    No Known Activations