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. 23301
    Prev
    Next
    INDEX
    Explanations

    instances where something or someone is distinguished as the sole or primary entity in a particular context

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating something is unique or one of many

    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
    excluding
    -0.65
     Respect
    -0.64
     Skydragon
    -0.64
    Progress
    -0.63
    hyd
    -0.63
    isters
    -0.62
    houses
    -0.61
    remember
    -0.60
     GENERAL
    -0.60
    ocene
    -0.60
    POSITIVE LOGITS
     bottleneck
    0.70
     anymore
    0.69
     cyn
    0.67
     sidel
    0.64
     nor
    0.64
     irony
    0.63
    .}
    0.63
    £ı
    0.62
     complication
    0.60
     harb
    0.60
    Activations Density 0.058%

    No Known Activations