© 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. 23708
    Prev
    Next
    INDEX
    Explanations

    references to a specific fictional television series

    oai_token-act-pair · gpt-3.5-turbo

    references to specific events and characters in 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 @ 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
    DAQ
    -0.92
     chirop
    -0.91
    Oregon
    -0.88
     HTC
    -0.88
     BART
    -0.87
    ierrez
    -0.85
     Tacoma
    -0.84
    bestos
    -0.83
    Pac
    -0.82
    TPP
    -0.82
    POSITIVE LOGITS
     Lann
    1.89
     Thrones
    1.80
     Wester
    1.78
     Ary
    1.61
     Jaime
    1.50
     Roose
    1.49
     Ramsay
    1.46
     Robb
    1.46
     HBO
    1.45
     Bran
    1.43
    Activations Density 0.267%

    No Known Activations