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. 3-RES-JB
    6. 1675
    Prev
    Next
    INDEX
    Explanations

    references to ninjas and samurais, indicating an interest in martial arts characters and themes

    oai_token-act-pair · gpt-3.5-turbo

    terms related to ninjas and samurai

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    itional
    -0.89
    Ö¼
    -0.87
    rigan
    -0.84
    sheet
    -0.83
    iments
    -0.79
    iday
    -0.77
    itably
    -0.76
    edly
    -0.74
    ochond
    -0.74
    odynam
    -0.73
    POSITIVE LOGITS
     Turtles
    1.19
     Ninja
    1.01
     Turtle
    0.93
     samurai
    0.88
     turtles
    0.88
     Samurai
    0.82
     Warrior
    0.79
     monk
    0.78
     sword
    0.75
     assassin
    0.74
    Activations Density 0.018%

    No Known Activations