© 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. 1-RES-JB
    11. 3389
    Prev
    Next
    INDEX
    Explanations

    websites to visit

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of calls to action for visiting websites or checking out content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ļé
    -0.74
    elf
    -0.72
     phyl
    -0.69
    arial
    -0.69
     orth
    -0.67
    ELF
    -0.67
     flatt
    -0.64
    raf
    -0.62
     bottleneck
    -0.62
     vanish
    -0.62
    POSITIVE LOGITS
     Visit
    0.95
     Watching
    0.88
     Check
    0.85
     Plus
    0.84
     Trailer
    0.83
     Upgrade
    0.82
     Look
    0.81
     Ready
    0.79
     Start
    0.79
     Here
    0.79
    Activations Density 0.022%

    No Known Activations