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. 20056
    Prev
    Next
    INDEX
    Explanations

    mentions of specific individuals, particularly those named Christine and Yanukovych

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    names of individuals, especially "Christine"

    oai_token-act-pair · gpt-3.5-turbo
    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
    leted
    -0.79
    tailed
    -0.79
    relation
    -0.77
    bed
    -0.76
    rection
    -0.76
    fork
    -0.76
    rito
    -0.75
    arity
    -0.74
    ersion
    -0.73
    nery
    -0.72
    POSITIVE LOGITS
     Carbuncle
    0.95
    ous
    0.94
     Dragonbound
    0.75
    pmwiki
    0.69
    é¾įåĸļ士
    0.68
     Strange
    0.64
    士
    0.64
    uous
    0.63
     Vari
    0.63
    shire
    0.63
    Activations Density 0.051%

    No Known Activations