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. 1-RES-JB
    6. 8306
    Prev
    Next
    INDEX
    Explanations

    words related to dealing with challenging situations or circumstances

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "cope" and its variations, indicating themes of resilience and dealing with challenges

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    reme
    -0.74
    ended
    -0.70
    cius
    -0.67
    enic
    -0.67
     Sight
    -0.66
    mining
    -0.65
    roma
    -0.65
    gone
    -0.65
    nic
    -0.63
    look
    -0.63
    POSITIVE LOGITS
     cope
    0.96
     adolesc
    0.93
     corrid
    0.91
     arrang
    0.90
     horizont
    0.89
    acebook
    0.83
     embr
    0.78
     coping
    0.77
     shenan
    0.77
     decomp
    0.74
    Activations Density 0.010%

    No Known Activations