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. 11943
    Prev
    Next
    INDEX
    Explanations

    terms related to institutions, especially higher education institutions

    oai_token-act-pair · gpt-3.5-turbo

    references to institutions, particularly their roles and characteristics

    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
     Rockies
    -0.74
    hner
    -0.70
    storms
    -0.69
    gets
    -0.68
     Powder
    -0.68
    THER
    -0.66
    atche
    -0.66
    ioxide
    -0.62
    ulf
    -0.62
    hab
    -0.62
    POSITIVE LOGITS
    itutional
    1.08
     institution
    0.96
    arians
    0.92
     institutions
    0.91
     Institution
    0.89
    ally
    0.86
    ually
    0.86
    utions
    0.84
    ional
    0.78
    opathic
    0.74
    Activations Density 0.021%

    No Known Activations