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. 13492
    Prev
    Next
    INDEX
    Explanations

    instances of the word "very"

    oai_token-act-pair · gpt-3.5-turbo

    extreme adjectives, particularly the word "very."

    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
    lees
    -0.96
     Releases
    -0.78
    aneers
    -0.76
    ses
    -0.73
     trophies
    -0.72
    ults
    -0.72
     purchases
    -0.72
     launchers
    -0.71
    agents
    -0.70
    ULTS
    -0.70
    POSITIVE LOGITS
     similar
    0.78
    technical
    0.77
     wide
    0.77
     representative
    0.75
     narrow
    0.75
     primitive
    0.74
     interesting
    0.73
     unique
    0.73
     characteristic
    0.71
     mixture
    0.71
    Activations Density 0.086%

    No Known Activations