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. 3842
    Prev
    Next
    INDEX
    Explanations

    phrases indicating attempts or efforts

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "trying."

    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
    orthy
    -0.71
     Included
    -0.67
    shall
    -0.64
     Amen
    -0.64
     correspond
    -0.62
     belongs
    -0.59
     Appropri
    -0.58
    rise
    -0.58
     coincides
    -0.58
    idence
    -0.58
    POSITIVE LOGITS
     trying
    3.03
     attempting
    2.51
     Trying
    2.10
     hoping
    1.80
     striving
    1.67
     pretending
    1.63
     seeking
    1.62
     try
    1.61
     wanting
    1.60
     searching
    1.55
    Activations Density 0.026%

    No Known Activations