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. 8181
    Prev
    Next
    INDEX
    Explanations

    fruit names

    oai_token-act-pair · gpt-3.5-turbo

    references to various types of fruits

    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
    hematic
    -0.82
    RAW
    -0.80
     condem
    -0.80
    kson
    -0.76
    ciplinary
    -0.73
    raq
    -0.71
    rict
    -0.70
    iazep
    -0.69
    earable
    -0.68
    gregation
    -0.68
    POSITIVE LOGITS
    fruit
    1.43
     fruit
    1.20
     juice
    1.15
     fruits
    1.13
     strawberries
    1.02
     cherry
    1.02
     tomatoes
    0.98
     mango
    0.97
     strawberry
    0.96
     juices
    0.95
    Activations Density 0.031%

    No Known Activations