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. 6539
    Prev
    Next
    INDEX
    Explanations

    phrases related to government or military programs

    oai_token-act-pair · gpt-3.5-turbo

    references to various surveillance and military programs

    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
    pick
    -0.75
    ModLoader
    -0.72
     dilig
    -0.71
     humidity
    -0.66
    è¦
    -0.65
    angelo
    -0.64
    CLASSIFIED
    -0.64
     Marketable
    -0.63
    poll
    -0.63
    picking
    -0.63
    POSITIVE LOGITS
    mable
    1.62
    matically
    1.38
    matic
    1.31
     Gutenberg
    0.96
    mers
    0.91
    eers
    0.87
    ional
    0.80
    heny
    0.79
    atical
    0.79
     instituted
    0.77
    Activations Density 0.028%

    No Known Activations