© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 4-RES-JB
    11. 6942
    Prev
    Next
    INDEX
    Explanations

    phrases welcoming the reader to different sections or topics

    oai_token-act-pair · gpt-3.5-turbo

    instances of the phrase "welcome to."

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

    No Comments

    Negative Logits
     dilig
    -0.75
     superflu
    -0.68
    ebted
    -0.67
    llo
    -0.66
     influenced
    -0.66
    framework
    -0.65
     relies
    -0.65
    conom
    -0.65
     affecting
    -0.65
    kowski
    -0.64
    POSITIVE LOGITS
    riott
    0.77
    lyn
    0.76
    asty
    0.74
     Welcome
    0.71
     Paradise
    0.68
    clus
    0.68
    erville
    0.66
     HIP
    0.66
     Fairy
    0.65
     Calm
    0.65
    Activations Density 0.098%

    No Known Activations