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. 7-RES-JB
    6. 13316
    Prev
    Next
    INDEX
    Explanations

    phrases related to waiting or anticipation

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "wa" and its variations, often indicating a focus on waiting or a state of being

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Luther
    -0.78
    rition
    -0.68
    nic
    -0.63
     FD
    -0.62
     portraying
    -0.58
     enlarge
    -0.58
     disinformation
    -0.57
    enegger
    -0.57
     geography
    -0.57
     inflicting
    -0.57
    POSITIVE LOGITS
    veland
    1.32
    pload
    1.17
    vel
    1.14
    uthor
    1.07
    ight
    1.06
    ccess
    1.06
    iving
    1.05
    ver
    1.01
    pless
    1.01
    fter
    1.01
    Activations Density 0.020%

    No Known Activations