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. 17682
    Prev
    Next
    INDEX
    Explanations

    the name "Dom" followed by varying suffixes

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns related to the name "Dom" or variations of it

    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
    doi
    -0.84
    bestos
    -0.82
    Bloom
    -0.78
     impe
    -0.78
     SPR
    -0.77
    mos
    -0.72
    ascular
    -0.71
     parach
    -0.70
     Oz
    -0.69
    ibrary
    -0.68
    POSITIVE LOGITS
     Dom
    3.22
     Domin
    2.18
     Dominion
    2.02
    Dom
    2.02
    Domin
    1.75
     Dominic
    1.57
     domin
    1.50
     Dominican
    1.43
     domination
    1.34
     dominion
    1.12
    Activations Density 0.041%

    No Known Activations