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. 11037
    Prev
    Next
    INDEX
    Explanations

    words related to something that is urgently required or a long-anticipated event

    oai_token-act-pair · gpt-3.5-turbo

    terms indicating necessity or urgent need

    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
    alos
    -0.77
    forums
    -0.72
    opers
    -0.72
    lua
    -0.71
    eligible
    -0.71
    uits
    -0.70
    arij
    -0.70
    builders
    -0.70
    paio
    -0.70
    flix
    -0.69
    POSITIVE LOGITS
     farewell
    0.82
     optimism
    0.79
     Parenthood
    0.76
     prosperity
    0.75
     birthday
    0.72
     wisdom
    0.71
     humanitarian
    0.69
     irony
    0.68
    ãĤ´ãĥ³
    0.68
     childhood
    0.68
    Activations Density 0.082%

    No Known Activations