© 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. 11-RES-JB
    11. 15754
    Prev
    Next
    INDEX
    Explanations

    words related to a specific TV show or franchise

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the TV 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 @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ought
    -0.66
    iffe
    -0.65
    ROR
    -0.62
    ancies
    -0.60
     bapt
    -0.59
    orate
    -0.58
     maxim
    -0.58
    attery
    -0.57
    hips
    -0.57
     Eisen
    -0.57
    POSITIVE LOGITS
    FAQ
    1.13
    Cube
    1.11
    Stop
    1.11
    zeb
    1.06
    Spot
    1.05
    cube
    1.04
    cock
    1.01
    Maker
    0.95
    boy
    0.94
     Freak
    0.90
    Activations Density 0.033%

    No Known Activations