© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 1-RES-JB
    11. 16284
    Prev
    Next
    INDEX
    Explanations

    keywords related to the term "Magic"

    oai_token-act-pair · gpt-3.5-turbo

    references to "Magic," specifically related to "Magic: The Gathering" or "Magic Kingdom."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     stern
    -0.73
    alez
    -0.71
     FEC
    -0.69
     CPC
    -0.67
     diver
    -0.64
    sg
    -0.64
     Fas
    -0.64
     unsub
    -0.63
     CFR
    -0.62
     fu
    -0.61
    POSITIVE LOGITS
    Magic
    1.03
     Magic
    1.00
     Leap
    0.87
    istry
    0.83
     Missile
    0.79
    eries
    0.77
    pedia
    0.77
    magic
    0.76
    ioned
    0.76
     Properties
    0.73
    Activations Density 0.006%

    No Known Activations