© 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. 4-RES-JB
    11. 10335
    Prev
    Next
    INDEX
    Explanations

    mentions or references to "parliament."

    oai_token-act-pair · gpt-3.5-turbo

    references to legislative bodies or parliaments

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

    No Comments

    Negative Logits
    ãģ¦
    -0.66
    ãģŁ
    -0.64
     Scouting
    -0.61
    uber
    -0.60
     Valhalla
    -0.60
     Meyer
    -0.59
     Stri
    -0.59
    CONT
    -0.59
     Intercept
    -0.59
    False
    -0.59
    POSITIVE LOGITS
    arians
    1.38
    arian
    1.10
    ional
    0.96
     parliament
    0.96
    liament
    0.95
    abulary
    0.86
    icians
    0.85
     Speaker
    0.85
    woman
    0.82
     impe
    0.82
    Activations Density 0.012%

    No Known Activations