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. 5-RES-JB
    6. 11268
    Prev
    Next
    INDEX
    Explanations

    mentions of infrastructure or related terms

    oai_token-act-pair · gpt-3.5-turbo

    references to infrastructure in various contexts

    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
    agher
    -0.87
    ishable
    -0.82
    onyms
    -0.82
    isher
    -0.78
    lee
    -0.76
    lon
    -0.76
    erer
    -0.75
    tein
    -0.73
    nery
    -0.73
    nee
    -0.73
    POSITIVE LOGITS
     infrastructure
    1.16
     Infrastructure
    0.94
     upkeep
    0.93
     redevelopment
    0.85
     connectivity
    0.83
     maintenance
    0.80
     backbone
    0.80
     resilience
    0.79
     investments
    0.79
     installations
    0.79
    Activations Density 0.027%

    No Known Activations