© 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. 6-RES-JB
    11. 10776
    Prev
    Next
    INDEX
    Explanations

    various mentions of specific individuals involved in political events

    oai_token-act-pair · gpt-3.5-turbo

    references to political figures and their actions related to investigations and meetings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ç¥ŀ
    -0.96
     ILCS
    -0.88
    byss
    -0.83
     Jagu
    -0.83
    liga
    -0.79
     kilomet
    -0.78
     Cure
    -0.77
     Riding
    -0.77
    Gra
    -0.76
     :(
    -0.74
    POSITIVE LOGITS
     CIA
    1.24
    ionage
    1.12
     subpoen
    1.10
     WikiLeaks
    1.10
     FBI
    1.08
    FBI
    1.07
     NSA
    1.07
     espionage
    1.07
     dossier
    1.06
     intelligence
    1.05
    Activations Density 1.163%

    No Known Activations