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. 1-RES-JB
    6. 14736
    Prev
    Next
    INDEX
    Explanations

    phrases related to serving or providing for others

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "serve" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    issues
    -0.74
    destruct
    -0.73
    pled
    -0.72
    orph
    -0.69
    amia
    -0.66
    eros
    -0.62
    aha
    -0.62
    orne
    -0.61
     uncontroll
    -0.60
    chy
    -0.59
    POSITIVE LOGITS
     Serving
    1.01
    Serv
    0.97
     SERV
    0.95
     Serve
    0.94
     serving
    0.90
     kitchens
    0.88
    HTTP
    0.88
    Ò
    0.86
     Restaur
    0.84
     serve
    0.84
    Activations Density 0.018%

    No Known Activations