© 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. 16444
    Prev
    Next
    INDEX
    Explanations

    phrases related to dragons

    oai_token-act-pair · gpt-3.5-turbo

    references to dragons

    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
    APD
    -0.84
    ERN
    -0.79
    ierrez
    -0.78
     Preferences
    -0.73
    oday
    -0.73
    rella
    -0.72
    EMS
    -0.72
    ADS
    -0.71
    CV
    -0.71
    Trend
    -0.69
    POSITIVE LOGITS
     dragons
    1.39
     dragon
    1.18
    flies
    1.12
    BuyableInstoreAndOnline
    1.04
    agons
    0.99
     Dragons
    0.97
    cffff
    0.92
     beasts
    0.89
    fly
    0.88
     ogre
    0.87
    Activations Density 0.007%

    No Known Activations