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. 6-RES-JB
    6. 21377
    Prev
    Next
    INDEX
    Explanations

    references to a specific character or brand named "Mega Man."

    oai_token-act-pair · gpt-3.5-turbo

    references to a specific video game franchise, particularly "Mega Man" and its various elements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    owship
    -0.95
    ually
    -0.87
    enance
    -0.84
    cies
    -0.79
    amental
    -0.78
    ional
    -0.77
    own
    -0.76
    lies
    -0.75
    oused
    -0.75
    iances
    -0.74
    POSITIVE LOGITS
     Punk
    1.02
     Zone
    0.93
     Fighters
    0.92
    Zero
    0.91
     Series
    0.89
     Panda
    0.88
    Works
    0.87
     Plus
    0.87
    Stream
    0.86
     Girl
    0.86
    Activations Density 0.072%

    No Known Activations