© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 4-RES-JB
    6. 15822
    Prev
    Next
    INDEX
    Explanations

    names of political figures

    oai_token-act-pair · gpt-3.5-turbo

    names of political figures and their associated roles

    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
    duc
    -0.77
    juries
    -0.74
     vag
    -0.69
     Savage
    -0.68
     miscarriage
    -0.68
     Occupations
    -0.67
     tavern
    -0.67
     DV
    -0.66
     Craigslist
    -0.66
     Prairie
    -0.65
    POSITIVE LOGITS
     Lavrov
    1.12
     deleg
    1.10
    ilateral
    1.09
     Jinping
    1.07
    plom
    1.06
     diplomacy
    0.99
     diplomats
    0.96
     Tillerson
    0.95
     envoy
    0.93
     diplomatic
    0.92
    Activations Density 0.272%

    No Known Activations