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. 23114
    Prev
    Next
    INDEX
    Explanations

    information related to economic status, rankings, and performance

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to economic rankings and positions of countries or regions

    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
     motions
    -0.72
     Elias
    -0.68
    thood
    -0.68
     illusions
    -0.68
     flares
    -0.67
     renovations
    -0.67
     Seah
    -0.66
    åħī
    -0.65
     Horowitz
    -0.65
     Nightmares
    -0.65
    POSITIVE LOGITS
     birthplace
    1.28
     country
    1.17
     nation
    1.14
     destination
    1.14
     superpower
    1.14
     countries
    1.11
     battleground
    1.02
     populous
    0.97
    country
    0.97
     nations
    0.96
    Activations Density 0.202%

    No Known Activations