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

    Neuronpedia

    APICircuit 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. 11-RES-JB
    6. 17763
    Prev
    Next
    INDEX
    Explanations

    the first things that come to mind in various situations

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate an initial thought or reaction

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    claimer
    -0.70
    still
    -0.69
    contin
    -0.67
    yet
    -0.66
    span
    -0.65
    Tags
    -0.64
    RW
    -0.63
    partial
    -0.62
    far
    -0.62
    vind
    -0.62
    POSITIVE LOGITS
     noticed
    0.94
     encountered
    0.82
     greeted
    0.78
     responders
    0.78
     ever
    0.76
     introdu
    0.76
     noticing
    0.72
     alerted
    0.72
    */(
    0.70
     realised
    0.69
    Activations Density 0.133%

    No Known Activations