© 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. 8553
    Prev
    Next
    INDEX
    Explanations

    positive adjectives describing something as exceptional or highly praiseworthy

    oai_token-act-pair · gpt-3.5-turbo

    expressions of high praise or positive sentiments

    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
    anwhile
    -0.69
    anamo
    -0.66
    Sources
    -0.65
    —"
    -0.64
    Correction
    -0.64
    Reporting
    -0.63
    uthor
    -0.62
    ocument
    -0.60
    nown
    -0.60
    itored
    -0.60
    POSITIVE LOGITS
     elegance
    1.16
     gorgeous
    1.11
     superb
    1.10
     versatility
    1.10
     flawless
    1.07
     versatile
    1.06
     exquisite
    1.06
     unbeat
    1.06
     flavorful
    1.06
     amazing
    1.05
    Activations Density 0.752%

    No Known Activations