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. 3-RES-JB
    6. 22066
    Prev
    Next
    INDEX
    Explanations

    words related to memory management in computer programming

    oai_token-act-pair · gpt-3.5-turbo

    references to computer memory management, specifically heaps and their related issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    psey
    -0.80
    igslist
    -0.78
     livest
    -0.72
    pee
    -0.72
    urnal
    -0.66
    yout
    -0.66
    æĹ
    -0.64
     sleeper
    -0.64
     estab
    -0.63
    pees
    -0.63
    POSITIVE LOGITS
    meyer
    0.95
    enger
    0.89
    ring
    0.82
    esville
    0.78
    fried
    0.78
     4090
    0.78
    nen
    0.76
    berg
    0.75
    enegger
    0.74
    stein
    0.74
    Activations Density 0.032%

    No Known Activations