© 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. 17912
    Prev
    Next
    INDEX
    Explanations

    positive actions or characteristics of individuals

    oai_token-act-pair · gpt-3.5-turbo

    actions and behaviors that demonstrate strong character or leadership

    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
    Enlarge
    -0.85
    winner
    -0.80
     guiActiveUnfocused
    -0.73
    hern
    -0.73
    ADVERTISEMENT
    -0.71
    eh
    -0.71
    toggle
    -0.68
    demand
    -0.68
    gypt
    -0.67
    apo
    -0.66
    POSITIVE LOGITS
     passionately
    0.78
     instinctively
    0.73
     wisely
    0.72
     constantly
    0.72
     extensively
    0.70
     tremendous
    0.70
     everything
    0.69
     moreover
    0.69
     effortlessly
    0.68
     friendships
    0.68
    Activations Density 0.531%

    No Known Activations