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. 1-RES-JB
    6. 19899
    Prev
    Next
    INDEX
    Explanations

    phrases related to the state of Nebraska

    oai_token-act-pair · gpt-3.5-turbo

    mentions of "Nebraska" and "Omaha"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    */(
    -0.81
    nings
    -0.72
    oss
    -0.71
    ials
    -0.71
    oured
    -0.70
    NUM
    -0.68
    ushes
    -0.66
    inals
    -0.66
    lass
    -0.66
    ablishment
    -0.66
    POSITIVE LOGITS
     Nebraska
    1.34
     Omaha
    1.14
    braska
    1.09
     Pryor
    0.94
     Wesley
    0.91
     Vaugh
    0.88
     Instruments
    0.87
     Petersen
    0.82
     Missouri
    0.81
    Minnesota
    0.81
    Activations Density 0.003%

    No Known Activations