© 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. 8-RES-JB
    11. 2472
    Prev
    Next
    INDEX
    Explanations

    phrases related to gaining or maintaining control or authority over something

    oai_token-act-pair · gpt-3.5-turbo

    phrases relating to the concept of "control" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Tale
    -0.69
    enegger
    -0.65
     Byr
    -0.64
    asus
    -0.63
    asca
    -0.63
     Serving
    -0.62
    geries
    -0.60
    Recommend
    -0.58
    uni
    -0.58
     Beir
    -0.57
    POSITIVE LOGITS
    orship
    1.04
    ership
    0.94
    eering
    0.90
    overs
    0.83
    lessness
    0.82
     control
    0.81
     thereof
    0.81
    ability
    0.81
    ANCE
    0.78
     levers
    0.76
    Activations Density 0.078%

    No Known Activations