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. 17591
    Prev
    Next
    INDEX
    Explanations

    phrases indicating future hypothetical scenarios

    oai_token-act-pair · gpt-3.5-turbo

    the word "would" indicating hypothetical situations or consequences

    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
    rylic
    -0.69
    æ³
    -0.68
    isted
    -0.64
    Reporting
    -0.62
     Basics
    -0.60
    oran
    -0.60
    Writing
    -0.60
     Jelly
    -0.60
    ished
    -0.59
     Case
    -0.59
    POSITIVE LOGITS
     surely
    1.01
     doubtless
    0.94
     never
    0.91
     be
    0.91
     undoubtedly
    0.90
     sugg
    0.89
     inevitably
    0.89
    ĸļ
    0.87
     imply
    0.86
     definitely
    0.82
    Activations Density 0.117%

    No Known Activations