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. 13051
    Prev
    Next
    INDEX
    Explanations

    mentions of specific research institutions, particularly Scripps Research Institute

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the term "cripple" and its variations

    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
     Antar
    -0.81
    isle
    -0.66
    izes
    -0.65
    ware
    -0.65
    izer
    -0.62
     Laden
    -0.62
     Corpus
    -0.61
    BW
    -0.61
    azar
    -0.59
     Tripoli
    -0.59
    POSITIVE LOGITS
    kefeller
    0.95
    erella
    0.89
    ulic
    0.88
    sburgh
    0.79
    nik
    0.77
    cens
    0.75
    eln
    0.75
    enthal
    0.75
    sylvania
    0.75
    mond
    0.72
    Activations Density 0.025%

    No Known Activations