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. 21612
    Prev
    Next
    INDEX
    Explanations

    phrases related to the Environmental Protection Agency (EPA)

    oai_token-act-pair · gpt-3.5-turbo

    references to the Environmental Protection Agency (EPA) and related discussions around its activities

    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
    orne
    -0.89
    hearted
    -0.74
    acters
    -0.74
    eners
    -0.71
     Dracula
    -0.70
    bones
    -0.68
    ties
    -0.67
    ax
    -0.66
     Samurai
    -0.65
     Hung
    -0.65
    POSITIVE LOGITS
    EPA
    1.14
     Administrator
    0.98
    sburg
    0.91
     EPA
    0.86
     administrator
    0.84
    uthor
    0.77
    gency
    0.76
    TN
    0.75
    ogl
    0.74
    acid
    0.73
    Activations Density 0.014%

    No Known Activations