© 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. 7-RES-JB
    11. 1973
    Prev
    Next
    INDEX
    Explanations

    phrases indicating satisfaction, approval, or emphasis

    oai_token-act-pair · gpt-3.5-turbo

    intensifiers expressing strong positive sentiments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    antry
    -0.89
    ansas
    -0.80
    heid
    -0.78
    arthed
    -0.67
     Receiver
    -0.67
    lessly
    -0.67
    arian
    -0.66
    adelphia
    -0.66
    icipated
    -0.66
    anwhile
    -0.65
    POSITIVE LOGITS
     appreciated
    0.77
     liked
    0.76
     pissed
    0.72
     messed
    0.72
     freaking
    0.72
     darn
    0.70
     fucking
    0.70
     fuckin
    0.70
    nice
    0.69
    FTWARE
    0.69
    Activations Density 0.056%

    No Known Activations