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. 7-RES-JB
    6. 4135
    Prev
    Next
    INDEX
    Explanations

    phrases related to critical commentary or sarcastic remarks

    oai_token-act-pair · gpt-3.5-turbo

    responses that convey strong opinions or judgments

    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
     footing
    -0.88
     intended
    -0.70
     jointly
    -0.66
    utive
    -0.66
     intending
    -0.65
     sailing
    -0.65
     funded
    -0.65
    arij
    -0.64
     discontin
    -0.62
    artney
    -0.62
    POSITIVE LOGITS
    Anyway
    1.24
    ³³³³³³³³
    1.10
    ³³³³³³³³³³³³³³³³
    1.07
    Thankfully
    1.02
    ³³³³
    1.01
    Moreover
    0.99
    Consider
    0.98
    Likewise
    0.97
    Unless
    0.97
    Nevertheless
    0.97
    Activations Density 0.398%

    No Known Activations