© 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. 10-RES-JB
    11. 10788
    Prev
    Next
    INDEX
    Explanations

    references to the TV show "Game of Thrones"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the show "Game of Thrones."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    orate
    -0.74
    etheless
    -0.74
    iffe
    -0.73
    ancies
    -0.70
    ought
    -0.68
    terday
    -0.65
    hips
    -0.64
    irst
    -0.63
    ORN
    -0.61
    taining
    -0.60
    POSITIVE LOGITS
    cube
    1.10
    Cube
    1.09
    FAQ
    1.07
    play
    1.05
    cock
    1.04
    Stop
    1.01
    zeb
    0.96
    boy
    0.92
    Spot
    0.91
     Developers
    0.89
    Activations Density 0.022%

    No Known Activations