© 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. 6986
    Prev
    Next
    INDEX
    Explanations

    references to different news channels and media outlets

    oai_token-act-pair · gpt-3.5-turbo

    mentions of television networks or channels

    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
     vein
    -0.69
    ewater
    -0.66
    pling
    -0.64
     appendix
    -0.63
    gone
    -0.63
     ineligible
    -0.62
     tee
    -0.62
     carts
    -0.61
    erto
    -0.61
     embargo
    -0.61
    POSITIVE LOGITS
     Europe
    0.92
    Aust
    0.90
    Europe
    0.90
     Japan
    0.90
     Australia
    0.90
     France
    0.88
    Asia
    0.88
     UK
    0.85
    Japan
    0.84
     Kuala
    0.84
    Activations Density 0.144%

    No Known Activations