Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & 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. 13721
    Prev
    Next
    INDEX
    Explanations

    social media interactions related to sharing or reposting

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "Ret", suggesting a focus on social media interactions or shares

    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
    tips
    -0.85
    ãĥ¼ãĥĨ
    -0.75
    STEM
    -0.74
    é¾įåĸļ士
    -0.68
    EngineDebug
    -0.67
     hearts
    -0.65
    hower
    -0.64
    ĪĴ
    -0.63
    ĨĴ
    -0.63
    aughtered
    -0.62
    POSITIVE LOGITS
    rieving
    1.07
    ribut
    1.06
    ention
    1.06
    ired
    1.06
    rieve
    1.05
    ract
    0.99
    ribution
    0.95
    reating
    0.94
    rieved
    0.93
    irement
    0.93
    Activations Density 0.008%

    No Known Activations