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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 0-RES-JB
    6. 4616
    Prev
    Next
    INDEX
    Explanations

    phrases related to dedication or commitment

    oai_token-act-pair · gpt-3.5-turbo

    references to commitments or specific initiatives focused on advocacy or support

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    igan
    -0.77
    anges
    -0.74
    oti
    -0.69
    Crunch
    -0.67
     Occupations
    -0.67
    ¶
    -0.67
    ett
    -0.66
    ey
    -0.65
     weaken
    -0.64
    çĶŁ
    -0.64
    POSITIVE LOGITS
     dedicated
    3.74
     devoted
    2.95
     dedicate
    2.27
     devote
    1.73
     dedication
    1.65
     specialized
    1.50
     Ded
    1.44
     focused
    1.35
     committed
    1.35
     reserved
    1.18
    Activations Density 0.017%

    No Known Activations