Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & 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. 16791
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to names, people, and characters

    oai_token-act-pair · gpt-3.5-turbo

    references to specific individuals, particularly those named Ariel, Amar, and Amir

    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
    book
    -0.83
    eding
    -0.80
    opic
    -0.73
    olith
    -0.72
    ongyang
    -0.72
    fighter
    -0.70
    books
    -0.70
    ures
    -0.69
    order
    -0.68
    buster
    -0.67
    POSITIVE LOGITS
     Levy
    0.77
     Castro
    0.77
     Chavez
    0.76
    ISO
    0.75
     Sharon
    0.74
    rawdownloadcloneembedreportprint
    0.74
     Netanyahu
    0.70
    ijah
    0.67
    icio
    0.67
     GOODMAN
    0.67
    Activations Density 0.044%

    No Known Activations