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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 4-RES-JB
    6. 12801
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to video games and characters

    oai_token-act-pair · gpt-3.5-turbo

    names of popular video game characters

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

    No Comments

    Negative Logits
    iances
    -0.91
    ENDED
    -0.76
    iance
    -0.76
     appliance
    -0.75
    iencies
    -0.73
    eredith
    -0.71
    umbn
    -0.70
    umbai
    -0.69
    ENE
    -0.67
    urgical
    -0.67
    POSITIVE LOGITS
     Kong
    1.05
     Donkey
    0.99
    Boss
    0.92
     Wii
    0.90
     Jr
    0.89
     Metroid
    0.88
    regate
    0.88
    hog
    0.84
     Bowser
    0.83
     Yoshi
    0.83
    Activations Density 0.020%

    No Known Activations