Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 16208
    Prev
    Next
    INDEX
    Explanations

    keywords related to news headlines, such as "Replay" and "Videos"

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "Replay" in relation to videos

    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
    kers
    -0.71
     sucker
    -0.71
    represented
    -0.70
    ult
    -0.70
    ker
    -0.69
    pora
    -0.65
    antle
    -0.65
     Mens
    -0.65
    EStreamFrame
    -0.64
    ide
    -0.64
    POSITIVE LOGITS
     WATCHED
    0.98
     Replay
    0.89
    natureconservancy
    0.73
     Lessons
    0.71
    icators
    0.71
     WATCH
    0.70
    querque
    0.69
     ï
    0.69
     Thumbnails
    0.69
    ique
    0.68
    Activations Density 0.012%

    No Known Activations