© 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. 3-RES-JB
    11. 560
    Prev
    Next
    INDEX
    Explanations

    names of political figures and officials

    oai_token-act-pair · gpt-3.5-turbo

    names of key political figures and advisors

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Collective
    -0.83
     Kop
    -0.78
     Jagu
    -0.72
    juries
    -0.69
     Century
    -0.67
     Squid
    -0.67
     vag
    -0.65
     denomin
    -0.64
    à¨
    -0.63
     Viking
    -0.63
    POSITIVE LOGITS
     aide
    1.01
     briefings
    1.00
    enei
    1.00
    eln
    0.97
     confid
    0.97
     briefed
    0.93
     Lavrov
    0.92
     memos
    0.91
     aides
    0.91
    andowski
    0.89
    Activations Density 0.055%

    No Known Activations