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

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & 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. 6-RES-JB
    6. 6560
    Prev
    Next
    INDEX
    Explanations

    instances of strong competition or opposition

    oai_token-act-pair · gpt-3.5-turbo

    terms related to competition and participation in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    atron
    -0.90
    mas
    -0.88
    bia
    -0.84
    notice
    -0.83
    chemy
    -0.82
    ascript
    -0.82
    iness
    -0.80
    imet
    -0.79
    ternity
    -0.79
    nery
    -0.77
    POSITIVE LOGITS
     alcoholic
    0.84
     agents
    0.84
     spouses
    0.82
     entities
    0.80
     heights
    0.80
     partners
    0.76
     adults
    0.76
     factions
    0.75
     competitors
    0.75
     viewpoints
    0.75
    Activations Density 0.185%

    No Known Activations