© 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. 7-RES-JB
    11. 7433
    Prev
    Next
    INDEX
    Explanations

    phrases related to political activities, conflicts, and social movements

    oai_token-act-pair · gpt-3.5-turbo

    connections to groups involved in illegal or controversial activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Character
    -0.77
    ĸļ
    -0.77
    tone
    -0.72
    ORD
    -0.72
    taker
    -0.72
    Story
    -0.71
    éĹĺ
    -0.70
    é¾įåĸļ士
    -0.66
     procedure
    -0.65
    IDENT
    -0.65
    POSITIVE LOGITS
     assorted
    0.91
     dictators
    0.89
     monsters
    0.89
     thugs
    0.88
     aliens
    0.88
     hybrids
    0.88
     migrants
    0.88
     allies
    0.87
     dissidents
    0.86
     mercenaries
    0.85
    Activations Density 0.275%

    No Known Activations