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. 19912
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "stone" in the text

    oai_token-act-pair · gpt-3.5-turbo

    references to the word "stone" in various contexts

    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
    oresc
    -0.91
    merce
    -0.87
    ersive
    -0.83
    ornia
    -0.83
    unct
    -0.81
    acy
    -0.76
    rha
    -0.76
     largeDownload
    -0.76
    orea
    -0.75
    inen
    -0.75
    POSITIVE LOGITS
     stone
    1.09
     stones
    1.02
    fish
    0.95
    hill
    0.94
    castle
    0.87
    lake
    0.86
    works
    0.86
     rocks
    0.85
    bats
    0.84
     slab
    0.83
    Activations Density 0.017%

    No Known Activations