© 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. 9-RES-JB
    11. 4315
    Prev
    Next
    INDEX
    Explanations

    positive moral attributes or qualities such as nobility and goodness

    oai_token-act-pair · gpt-3.5-turbo
    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
    aq
    -0.75
    esville
    -0.74
    ingo
    -0.72
    oan
    -0.70
    ing
    -0.69
     Controlled
    -0.68
    olina
    -0.67
    aby
    -0.67
    olver
    -0.65
    yss
    -0.65
    POSITIVE LOGITS
     deeds
    1.12
     intentions
    0.97
    minded
    0.93
     laureate
    0.93
     indignation
    0.89
     gentlemen
    0.88
     virtues
    0.87
     minded
    0.87
     gentleman
    0.87
     pursuits
    0.85
    Activations Density 0.196%

    No Known Activations