© 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. 7770
    Prev
    Next
    INDEX
    Explanations

    simple instructions or commands starting with the word "Just"

    oai_token-act-pair · gpt-3.5-turbo

    the use of the word "just" and its variations in instructional or explanatory contexts

    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
    ylum
    -0.70
    SPONSORED
    -0.68
     developments
    -0.67
    development
    -0.66
     havoc
    -0.65
    Development
    -0.65
    Scar
    -0.63
    sein
    -0.63
    anty
    -0.63
     Pett
    -0.61
    POSITIVE LOGITS
     click
    0.99
     kidding
    0.91
     CLICK
    0.91
     flick
    0.88
     swipe
    0.85
     ask
    0.84
     select
    0.83
     browse
    0.80
     apply
    0.80
     activate
    0.79
    Activations Density 0.061%

    No Known Activations