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. 23613
    Prev
    Next
    INDEX
    Explanations

    phrases related to organizing tasks, events, or people

    oai_token-act-pair · gpt-3.5-turbo

    actions related to coordination and organization efforts

    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
     continued
    -0.70
     being
    -0.66
     supposed
    -0.65
     dating
    -0.64
    going
    -0.63
     left
    -0.62
     living
    -0.62
     Continued
    -0.62
     coming
    -0.62
     sustained
    -0.62
    POSITIVE LOGITS
     organize
    1.83
     simplify
    1.81
     analyze
    1.79
     optimize
    1.79
     organise
    1.79
     integrate
    1.79
     automate
    1.78
     allocate
    1.74
     circulate
    1.74
     stabilize
    1.73
    Activations Density 0.165%

    No Known Activations