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. 10-RES-JB
    6. 15213
    Prev
    Next
    INDEX
    Explanations

    phrases expressing various emotions, often related to disappointment, surprise, or a mixture of feelings

    oai_token-act-pair · gpt-3.5-turbo

    expressions of strong emotional reactions, particularly disappointment and surprise

    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
    Fact
    -0.72
    aband
    -0.68
    querade
    -0.66
     specialization
    -0.65
     roam
    -0.63
     Slot
    -0.62
     Prevent
    -0.62
     expires
    -0.62
     routes
    -0.62
     Proper
    -0.62
    POSITIVE LOGITS
     dismay
    1.71
     appalled
    1.68
     amazed
    1.67
     astonished
    1.65
     thrilled
    1.64
     horrified
    1.62
     disappointed
    1.62
     saddened
    1.60
     delighted
    1.59
     ecstatic
    1.58
    Activations Density 0.438%

    No Known Activations