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. 9452
    Prev
    Next
    INDEX
    Explanations

    configurations and instructions related to software development

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "to" indicating commands or actions

    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
    stories
    -0.71
     prosecutions
    -0.70
    hur
    -0.66
    riots
    -0.66
    living
    -0.64
    itarian
    -0.63
    tions
    -0.60
    iberal
    -0.60
     kisses
    -0.59
    national
    -0.59
    POSITIVE LOGITS
    ggles
    1.40
     maximize
    1.13
     optimize
    1.09
     activate
    1.05
     ensure
    1.05
     minimize
    1.04
     simulate
    1.03
     determine
    0.99
     emulate
    0.98
     modify
    0.98
    Activations Density 0.354%

    No Known Activations