Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 0-RES-JB
    6. 10554
    Prev
    Next
    INDEX
    Explanations

    words or phrases with the letters "se" in them

    oai_token-act-pair · gpt-3.5-turbo

    the plural form of the verb "to be."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    WARE
    -0.76
     DM
    -0.60
     clocks
    -0.60
     Directors
    -0.60
     TM
    -0.60
     dots
    -0.58
     Monsters
    -0.57
     [(
    -0.56
     downhill
    -0.56
     cannon
    -0.56
    POSITIVE LOGITS
    se
    4.29
    SE
    1.93
    sem
    1.70
    ses
    1.66
    Se
    1.57
    seed
    1.51
    sey
    1.44
    sei
    1.37
    sein
    1.34
     Se
    1.33
    Activations Density 0.018%

    No Known Activations