© 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. 17168
    Prev
    Next
    INDEX
    Explanations

    dates or events related to holidays or ceremonies

    oai_token-act-pair · gpt-3.5-turbo

    references to "Memorial Day" and related observances

    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
     glim
    -0.77
    collar
    -0.76
     crate
    -0.73
    otto
    -0.72
    umbn
    -0.71
     collar
    -0.68
    atorial
    -0.67
    ierrez
    -0.67
    ural
    -0.66
    urally
    -0.65
    POSITIVE LOGITS
    dream
    1.16
     Day
    0.99
     Massacre
    0.90
     Patrol
    0.86
     Parade
    0.83
    flower
    0.83
    day
    0.82
     Weekend
    0.79
     Marathon
    0.76
    Day
    0.76
    Activations Density 0.019%

    No Known Activations