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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 1379
    Prev
    Next
    INDEX
    Explanations

    websites, movements, or organizations dedicated to a particular cause or theme

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating a dedication or commitment to various causes or topics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    epend
    -0.78
     retracted
    -0.72
     swayed
    -0.72
    loo
    -0.69
     triggered
    -0.63
    isp
    -0.62
     boarded
    -0.62
    met
    -0.61
    techn
    -0.61
    comings
    -0.60
    POSITIVE LOGITS
    othy
    0.81
     preserving
    0.80
     Purpose
    0.79
    icial
    0.71
     dedicate
    0.69
     honoring
    0.67
     Virtue
    0.67
    ternity
    0.67
     maximize
    0.67
     honor
    0.66
    Activations Density 0.077%

    No Known Activations