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. 10551
    Prev
    Next
    INDEX
    Explanations

    words related to a specific type of competition or structure with eight sides

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "agon" or its variants in various contexts

    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
     neglect
    -0.64
     hrs
    -0.63
     remote
    -0.63
     immersion
    -0.62
     recy
    -0.61
     sprink
    -0.61
     misdem
    -0.61
     Runtime
    -0.59
     rese
    -0.59
     TIM
    -0.59
    POSITIVE LOGITS
    agon
    4.78
    agons
    2.50
    agonal
    2.02
    agen
    1.39
    agram
    1.35
    itol
    1.06
    aban
    1.00
    agonist
    0.99
    igon
    0.97
    agra
    0.97
    Activations Density 0.013%

    No Known Activations