© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 0-RES-JB
    11. 7799
    Prev
    Next
    INDEX
    Explanations

    references to a specific political organization

    oai_token-act-pair · gpt-3.5-turbo

    references to the political party Sinn Féin and related political entities or events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ulia
    -0.85
     Alexa
    -0.81
     Yak
    -0.77
     Nex
    -0.74
     eval
    -0.71
     Kodi
    -0.69
    omez
    -0.68
     Zel
    -0.68
    Alex
    -0.68
     webcam
    -0.67
    POSITIVE LOGITS
     Sinn
    3.41
     DUP
    1.93
     IRA
    1.80
     Fine
    1.76
     Gerry
    1.65
     TDs
    1.35
     Sands
    1.31
     Ulster
    1.27
    inness
    1.26
     Tao
    1.25
    Activations Density 0.067%

    No Known Activations