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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 16448
    Prev
    Next
    INDEX
    Explanations

    instances of physical struggle or conflict

    oai_token-act-pair · gpt-3.5-turbo

    the conjunction "and" specifically in various contexts

    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
    odcast
    -0.69
    udo
    -0.67
    Times
    -0.66
    unique
    -0.64
     Dating
    -0.64
    NULL
    -0.63
    ãĥķãĤ¡
    -0.62
    duino
    -0.62
    ADVERTISEMENT
    -0.62
    Different
    -0.62
    POSITIVE LOGITS
     began
    1.05
     proceeded
    1.05
     gave
    1.00
     then
    0.99
     eventually
    0.98
     stayed
    0.95
     became
    0.95
     drove
    0.94
     promptly
    0.94
     consequently
    0.94
    Activations Density 0.290%

    No Known Activations