Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 17096
    Prev
    Next
    INDEX
    Explanations

    countries and nationalities

    oai_token-act-pair · gpt-3.5-turbo

    references to nationalities and their relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     outputs
    -0.73
    :[
    -0.72
     teamwork
    -0.67
     thresholds
    -0.64
     Staples
    -0.64
     Starr
    -0.63
     airflow
    -0.62
     stalls
    -0.62
     adequ
    -0.61
     responsiveness
    -0.61
    POSITIVE LOGITS
    onian
    0.79
    eno
    0.79
    Balt
    0.78
    rencies
    0.77
    speaking
    0.74
    Rail
    0.73
     Liberties
    0.72
    ño
    0.71
     Ale
    0.70
    English
    0.70
    Activations Density 0.401%

    No Known Activations