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. 5499
    Prev
    Next
    INDEX
    Explanations

    instances where the document instructs the reader to take a look at something

    oai_token-act-pair · gpt-3.5-turbo

    instances of the phrase "take a look."

    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
    necess
    -0.73
    upuncture
    -0.68
    ortunately
    -0.66
    coal
    -0.66
    ply
    -0.64
    claimed
    -0.63
    Chart
    -0.62
     Methods
    -0.61
    GA
    -0.61
    Staff
    -0.60
    POSITIVE LOGITS
    ahead
    0.75
    finder
    0.74
    atio
    0.71
     ãĤ
    0.70
    iger
    0.67
    iang
    0.65
    ative
    0.64
     look
    0.64
    emark
    0.63
    ãĤ¶
    0.63
    Activations Density 0.016%

    No Known Activations