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. 12102
    Prev
    Next
    INDEX
    Explanations

    words related to communication, such as speakers, listeners, reports, and feedback

    oai_token-act-pair · gpt-3.5-turbo

    repeated punctuation marks, particularly commas, indicating a pattern or emphasis in the text

    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
    units
    -0.65
    ļéĨĴ
    -0.64
    Goal
    -0.59
    interstitial
    -0.59
    aha
    -0.59
    Override
    -0.59
    Reward
    -0.59
    Reply
    -0.57
    account
    -0.57
    Engineers
    -0.55
    POSITIVE LOGITS
     huh
    1.06
     however
    1.03
     sir
    0.87
     albeit
    0.86
     please
    0.82
     though
    0.81
     eh
    0.80
     meanwhile
    0.80
     yes
    0.73
     yeah
    0.70
    Activations Density 0.463%

    No Known Activations