© 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. 4-RES-JB
    11. 7819
    Prev
    Next
    INDEX
    Explanations

    terms related to the TV show "Game of Thrones"

    oai_token-act-pair · gpt-3.5-turbo

    references to the "Game of Thrones" series

    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
    iffe
    -0.83
     staffed
    -0.74
    terday
    -0.73
    Downloadha
    -0.73
    ishable
    -0.72
    undai
    -0.71
     chem
    -0.69
    rower
    -0.69
    irst
    -0.68
     dotted
    -0.68
    POSITIVE LOGITS
    cube
    1.05
    play
    0.98
    Maker
    0.96
    Spot
    0.89
     Nerd
    0.88
     Clash
    0.86
    pad
    0.86
    Cube
    0.86
     Game
    0.83
     Genie
    0.82
    Activations Density 0.021%

    No Known Activations