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. 11779
    Prev
    Next
    INDEX
    Explanations

    words related to identification and travel documents, specifically focusing on the term "Pass."

    oai_token-act-pair · gpt-3.5-turbo

    references to the Passover holiday

    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
    ãĤ¼ãĤ¦ãĤ¹
    -1.03
    ä¸ī
    -0.83
     GOODMAN
    -0.71
     ASP
    -0.62
     rook
    -0.62
     Cortex
    -0.61
     PLA
    -0.60
     Pwr
    -0.60
     Admir
    -0.59
     Kut
    -0.58
    POSITIVE LOGITS
    engers
    1.44
    wd
    1.30
    enger
    1.27
    words
    1.13
    es
    1.10
    ioned
    1.05
    aic
    1.05
    ports
    1.04
    port
    0.95
    phrase
    0.93
    Activations Density 0.016%

    No Known Activations