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

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & 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. 14791
    Prev
    Next
    INDEX
    Explanations

    phrases related to service or serving

    oai_token-act-pair · gpt-3.5-turbo

    words related to service and servitude

    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
     prone
    -0.64
     Kubrick
    -0.64
     fertile
    -0.63
     heavier
    -0.61
     curly
    -0.60
     dense
    -0.60
     heaviest
    -0.59
     Pound
    -0.59
    razil
    -0.59
     invasive
    -0.59
    POSITIVE LOGITS
    serv
    1.22
    iced
    1.22
    maid
    1.00
    icer
    0.97
    icing
    0.96
    iments
    0.95
     serv
    0.95
    Serv
    0.90
     Serv
    0.88
    itor
    0.87
    Activations Density 0.016%

    No Known Activations