© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 9-RES-JB
    11. 17945
    Prev
    Next
    INDEX
    Explanations

    comparisons between different groups or populations based on certain criteria

    oai_token-act-pair · gpt-3.5-turbo

    references to women and their circumstances in comparison to others

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ruining
    -0.73
     pandemonium
    -0.70
     elegance
    -0.70
     ramifications
    -0.69
     repercussions
    -0.69
     shenanigans
    -0.69
     madness
    -0.68
     amidst
    -0.68
     pitfalls
    -0.66
     contradictions
    -0.65
    POSITIVE LOGITS
     participated
    1.09
     underwent
    1.03
     enrolled
    0.97
    ivari
    0.94
     volunteered
    0.91
    pleted
    0.89
     receive
    0.88
     completed
    0.88
     attended
    0.88
     graduated
    0.88
    Activations Density 0.221%

    No Known Activations