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. 10-RES-JB
    6. 18066
    Prev
    Next
    INDEX
    Explanations

    information related to combat sports events and fighters

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to combat sports and matchups

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    inventory
    -0.86
    psc
    -0.83
    isans
    -0.80
    seys
    -0.80
    church
    -0.79
    politics
    -0.78
    wcs
    -0.77
    iculture
    -0.75
    HUD
    -0.74
    cffff
    -0.74
    POSITIVE LOGITS
     Dustin
    1.24
     Sergey
    1.22
     Alberto
    1.20
     Juan
    1.17
     Viktor
    1.17
     Jorge
    1.16
     Akira
    1.15
     Leonardo
    1.14
     Vladimir
    1.14
     Sonny
    1.12
    Activations Density 0.128%

    No Known Activations