© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 9-RES-JB
    11. 15411
    Prev
    Next
    INDEX
    Explanations

    power dynamics, political maneuvers, and social issues in text

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate manipulation and exploitation for personal or political gain

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    çīĪ
    -0.68
    tackle
    -0.67
     Explore
    -0.63
    webkit
    -0.63
     Methodist
    -0.63
     Crusher
    -0.63
    "}],"
    -0.62
     surveyed
    -0.61
     Alloy
    -0.61
     Loving
    -0.61
    POSITIVE LOGITS
     agendas
    0.97
     pretext
    0.97
     blackmail
    0.95
     profit
    0.95
     agenda
    0.93
     nefarious
    0.88
     revenge
    0.88
     advantage
    0.87
     predetermined
    0.87
     profits
    0.85
    Activations Density 0.735%

    No Known Activations