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. 5975
    Prev
    Next
    INDEX
    Explanations

    mentions of products or entities involving the term "ener" and slight variations, such as "energetically" or "sweeteners."

    oai_token-act-pair · gpt-3.5-turbo

    variations of the word "energetic" and its related forms

    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
     Clerk
    -0.68
     Editors
    -0.66
    INESS
    -0.63
     translating
    -0.62
     Visitors
    -0.61
     Occupations
    -0.60
     translated
    -0.59
    quote
    -0.58
     Blow
    -0.58
    wordpress
    -0.58
    POSITIVE LOGITS
    getic
    1.10
    oneliness
    0.85
    éĹĺ
    0.84
    amic
    0.81
    atives
    0.81
    rors
    0.77
     ende
    0.76
    ener
    0.76
    ation
    0.76
    ļéĨĴ
    0.75
    Activations Density 0.015%

    No Known Activations