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. 7322
    Prev
    Next
    INDEX
    Explanations

    phrases related to community involvement and social contributions

    oai_token-act-pair · gpt-3.5-turbo

    discussions around inclusion and contributions to society

    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
    iple
    -0.52
    çͰ
    -0.51
    Nit
    -0.51
    amount
    -0.50
     largeDownload
    -0.49
    SourceFile
    -0.49
     Converted
    -0.48
    Strike
    -0.47
    DragonMagazine
    -0.47
    ortium
    -0.46
    POSITIVE LOGITS
    equality
    0.57
     paycheck
    0.55
     anymore
    0.53
     frivolous
    0.52
     cheaply
    0.51
     anytime
    0.50
     or
    0.50
     advantageous
    0.50
     oneself
    0.49
     disadvantaged
    0.49
    Activations Density 2.288%

    No Known Activations