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. 13241
    Prev
    Next
    INDEX
    Explanations

    extended phrases containing a verb "said"

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "said."

    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
    otion
    -0.76
    xtap
    -0.74
    pleting
    -0.71
    email
    -0.68
    \/\/
    -0.68
    physical
    -0.67
    oppable
    -0.67
    EMBER
    -0.67
    amac
    -0.65
    Issue
    -0.64
    POSITIVE LOGITS
     goodbye
    0.84
     yesterday
    0.73
     bluntly
    0.68
     aloud
    0.63
     repeatedly
    0.62
     Monday
    0.62
     Wednesday
    0.61
     earlier
    0.60
     Tuesday
    0.60
     emphatically
    0.59
    Activations Density 0.191%

    No Known Activations