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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 10-RES-JB
    6. 3236
    Prev
    Next
    INDEX
    Explanations

    words related to negative emotions or situations

    oai_token-act-pair · gpt-3.5-turbo

    negative descriptors related to discomfort or irritation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    uilding
    -0.90
    arnaev
    -0.89
    icrobial
    -0.83
    emis
    -0.81
    zsche
    -0.81
    overe
    -0.80
    orah
    -0.80
    agogue
    -0.79
    bold
    -0.79
    acebook
    -0.79
    POSITIVE LOGITS
     nuisance
    0.97
     ted
    0.96
     annoyance
    0.94
     headaches
    0.91
     annoy
    0.91
    ness
    0.88
    nesses
    0.88
     truths
    0.88
     reminders
    0.88
     surprises
    0.88
    Activations Density 0.112%

    No Known Activations