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. 10-RES-JB
    6. 254
    Prev
    Next
    INDEX
    Explanations

    phrases related to memory retrieval and revisiting past experiences

    oai_token-act-pair · gpt-3.5-turbo

    references to personal experiences and memories

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    osi
    -0.70
     watchdog
    -0.68
     Supporters
    -0.64
     pricing
    -0.62
     regulators
    -0.62
     moderates
    -0.61
    taboola
    -0.61
    efficiency
    -0.61
     antitrust
    -0.59
     recommendations
    -0.59
    POSITIVE LOGITS
     millennia
    1.07
     ancestors
    1.04
     previous
    1.00
     childhood
    1.00
    terday
    0.98
     ago
    0.97
     centuries
    0.94
     beforehand
    0.92
     past
    0.91
     lived
    0.89
    Activations Density 0.496%

    No Known Activations