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. 8-RES-JB
    6. 21809
    Prev
    Next
    INDEX
    Explanations

    instances of transition in actions or events

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating the beginning of actions or processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Carlton
    -0.65
     Valent
    -0.65
    prem
    -0.64
    TED
    -0.62
     Walters
    -0.62
    quickShipAvailable
    -0.62
    yet
    -0.62
     Guardian
    -0.60
     Gateway
    -0.58
     Malf
    -0.58
    POSITIVE LOGITS
     resemble
    1.18
     realize
    1.08
     accumulate
    1.08
     soften
    1.01
     dismantle
    0.98
     realise
    0.98
     unravel
    0.98
     settle
    0.96
     lose
    0.96
     recognize
    0.96
    Activations Density 0.068%

    No Known Activations