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. 16150
    Prev
    Next
    INDEX
    Explanations

    variations of the word 'diaspora'

    oai_token-act-pair · gpt-3.5-turbo

    repeated occurrences of the substring "ias."

    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
    ishment
    -0.85
    ishers
    -0.85
    ishing
    -0.79
    ishable
    -0.76
    orney
    -0.75
    iddler
    -0.73
    ered
    -0.70
    erer
    -0.69
    ished
    -0.68
    lished
    -0.66
    POSITIVE LOGITS
    pora
    1.36
    aurus
    0.89
    pend
    0.86
    leep
    0.84
    metics
    0.79
    cules
    0.78
    oft
    0.78
    phal
    0.77
    lda
    0.75
    sembly
    0.75
    Activations Density 0.019%

    No Known Activations