© 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. 2-RES-JB
    11. 5385
    Prev
    Next
    INDEX
    Explanations

    words related to the concept of "premises" or "premiership"

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of "premiership" or "premature."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    glers
    -0.97
     Tid
    -0.81
     MacArthur
    -0.80
    ger
    -0.76
    gers
    -0.75
    meyer
    -0.75
    ARB
    -0.73
     Mae
    -0.72
     Wiley
    -0.72
    gerald
    -0.71
    POSITIVE LOGITS
     prem
    1.08
    iership
    1.05
    antle
    1.00
    ises
    0.98
    ortal
    0.98
    Prem
    0.95
    prem
    0.94
    igrate
    0.93
     unden
    0.87
    inarily
    0.86
    Activations Density 0.007%

    No Known Activations