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. 17809
    Prev
    Next
    INDEX
    Explanations

    words related to the name "Nip"

    oai_token-act-pair · gpt-3.5-turbo

    references to "nip."

    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
    DERR
    -0.84
     Dying
    -0.78
    é¾
    -0.78
     EntityItem
    -0.77
     Admir
    -0.74
    âĸ¬
    -0.72
     Aval
    -0.72
    DEV
    -0.71
    Ùİ
    -0.70
    taboola
    -0.69
    POSITIVE LOGITS
    artisan
    1.21
    osit
    1.21
    otent
    1.12
    ython
    1.07
    inion
    1.07
    arent
    1.07
    osition
    1.04
    nir
    1.03
    uls
    1.00
    osite
    0.99
    Activations Density 0.018%

    No Known Activations