Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 10-RES-JB
    6. 2002
    Prev
    Next
    INDEX
    Explanations

    positive personality traits in people

    oai_token-act-pair · gpt-3.5-turbo

    adjectives describing positive personality traits

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    ortmund
    -0.98
    çīĪ
    -0.91
    ciation
    -0.88
    ulia
    -0.84
    ptoms
    -0.82
    ancial
    -0.82
     Skydragon
    -0.81
    osate
    -0.80
    okia
    -0.78
    veyard
    -0.77
    POSITIVE LOGITS
     witty
    1.55
     intelligent
    1.47
     fearless
    1.46
     courageous
    1.46
     compassionate
    1.45
     charismatic
    1.44
     energetic
    1.41
     adventurous
    1.39
     respectful
    1.38
     insightful
    1.37
    Activations Density 0.227%

    No Known Activations