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. 0-RES-JB
    6. 10550
    Prev
    Next
    INDEX
    Explanations

    attempts or efforts to do something

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "attempts."

    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
    ird
    -0.71
    rette
    -0.64
    âĺ
    -0.62
    picture
    -0.61
    cum
    -0.59
     backbone
    -0.59
    Safety
    -0.58
    Ïī
    -0.57
    cloth
    -0.57
    quarter
    -0.57
    POSITIVE LOGITS
     attempts
    3.68
     attempt
    2.61
     efforts
    2.17
     Attempt
    2.15
    Attempts
    2.03
     attempted
    1.94
     tries
    1.88
     endeavors
    1.78
    Attempt
    1.73
     attempting
    1.71
    Activations Density 0.009%

    No Known Activations