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. 5-RES-JB
    6. 731
    Prev
    Next
    INDEX
    Explanations

    mentions of the University of California

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the University of California system and its campuses

    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
    paio
    -0.72
    warm
    -0.71
     bins
    -0.66
    odan
    -0.66
     grocer
    -0.64
    */(
    -0.64
    bread
    -0.63
    oÄŁan
    -0.63
    netflix
    -0.62
     phrases
    -0.62
    POSITIVE LOGITS
     Robotics
    0.77
     Laboratories
    0.76
     Athletic
    0.76
     Extension
    0.75
    uthor
    0.70
     Ethics
    0.70
     Applied
    0.69
     Computing
    0.69
    ortunately
    0.69
    UTH
    0.68
    Activations Density 0.052%

    No Known Activations