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. 9-RES-JB
    6. 20583
    Prev
    Next
    INDEX
    Explanations

    phrases related to events starting or initiating

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to the beginning of events or activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    usercontent
    -0.72
    founded
    -0.65
     risked
    -0.65
    elling
    -0.64
    finder
    -0.64
    alogy
    -0.64
     contracted
    -0.62
     incurred
    -0.62
     replicated
    -0.60
     Attribution
    -0.60
    POSITIVE LOGITS
     festivities
    0.98
     countdown
    0.82
     celebrations
    0.82
    mble
    0.79
     SX
    0.79
    season
    0.77
     ceremonies
    0.76
    Ń·
    0.76
     EDITION
    0.75
    ĻĤ
    0.74
    Activations Density 0.149%

    No Known Activations