© 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. 10-RES-JB
    11. 18683
    Prev
    Next
    INDEX
    Explanations

    phrases related to actions done in the name of a certain cause or authority

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Cosponsors
    -0.80
    igue
    -0.79
    oor
    -0.77
    iaries
    -0.75
    ards
    -0.73
    iste
    -0.70
    ask
    -0.69
    jad
    -0.68
    aves
    -0.67
    read
    -0.67
    POSITIVE LOGITS
     protecting
    0.91
     preserving
    0.90
     facilitating
    0.87
     combating
    0.85
     promoting
    0.84
     advancing
    0.84
     enhancing
    0.83
     aiding
    0.81
     improving
    0.81
     sheer
    0.81
    Activations Density 0.156%

    No Known Activations