© 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. 24086
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to diplomatic discussions and agreements

    oai_token-act-pair · gpt-3.5-turbo

    key statements regarding political intentions and commitments related to the EU

    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
     Arkansas
    -0.89
    igham
    -0.87
     Brigham
    -0.84
    aroo
    -0.82
     Hancock
    -0.80
     Forrest
    -0.80
    Ark
    -0.79
     Mormon
    -0.78
     Pryor
    -0.77
    ollah
    -0.77
    POSITIVE LOGITS
     EU
    2.22
     Brussels
    2.11
    EU
    1.95
     MEP
    1.90
     European
    1.85
     Europe
    1.82
     eurozone
    1.82
     Europeans
    1.80
     euro
    1.80
    European
    1.77
    Activations Density 0.728%

    No Known Activations