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. 19715
    Prev
    Next
    INDEX
    Explanations

    phrases related to desires and preferences

    oai_token-act-pair · gpt-3.5-turbo

    expressions of desire or wants from various subjects

    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
    ovember
    -0.88
    iatus
    -0.80
    farious
    -0.71
    esan
    -0.70
    ogenesis
    -0.69
    代
    -0.67
    soDeliveryDate
    -0.67
    ruary
    -0.66
    acerb
    -0.65
    ondo
    -0.65
    POSITIVE LOGITS
     consistency
    1.02
     simplicity
    1.01
     something
    1.00
     flexibility
    1.00
     certainty
    0.97
     stability
    0.96
     reliable
    0.95
     clarity
    0.93
     assurance
    0.93
     predictable
    0.90
    Activations Density 0.159%

    No Known Activations