© 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. 8401
    Prev
    Next
    INDEX
    Explanations

    personal well-being and success-related phrases

    oai_token-act-pair · gpt-3.5-turbo
    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
     obscure
    -0.95
     whiff
    -0.95
     intu
    -0.91
     sucker
    -0.90
     piled
    -0.89
     tangled
    -0.89
     imperson
    -0.88
     unintended
    -0.86
     fancy
    -0.85
     sprung
    -0.84
    POSITIVE LOGITS
    ï¸ı
    1.57
    ï¸
    1.19
    Thank
    1.16
     Thank
    1.14
    <|endoftext|>
    1.10
    ###
    1.10
    ðŁ
    1.08
    Our
    1.04
    Visit
    1.04
    âĢİ
    1.02
    Activations Density 0.228%

    No Known Activations