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. 5488
    Prev
    Next
    INDEX
    Explanations

    statements related to food and economics

    oai_token-act-pair · gpt-3.5-turbo

    references to food and its qualities or conditions

    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
     ACTIONS
    -0.61
     Universities
    -0.60
     Students
    -0.58
     martial
    -0.58
     Student
    -0.57
     Talent
    -0.55
     Colleges
    -0.55
    USS
    -0.54
    Students
    -0.54
     Intervention
    -0.52
    POSITIVE LOGITS
     oxid
    0.87
    ufact
    0.74
     fertil
    0.72
     processed
    0.69
     consumed
    0.69
     combustion
    0.69
     corro
    0.68
     ingested
    0.66
     harvested
    0.65
     chemically
    0.65
    Activations Density 1.056%

    No Known Activations