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. 10503
    Prev
    Next
    INDEX
    Explanations

    phrases mentioning a specific individual named Kim

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the name "Kim" and related individuals

    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
     cardinal
    -0.75
     dra
    -0.74
     saddle
    -0.69
     Avalanche
    -0.68
     senses
    -0.68
     Tus
    -0.68
     cavalry
    -0.67
     encl
    -0.67
     basil
    -0.67
     sector
    -0.66
    POSITIVE LOGITS
    Kim
    3.58
     Kim
    2.15
     Kimberly
    1.52
     Kimber
    1.44
     Choi
    1.37
    Lee
    1.32
    jong
    1.29
     Koreans
    1.18
     Pyongyang
    1.17
     DPRK
    1.17
    Activations Density 0.021%

    No Known Activations