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. 21901
    Prev
    Next
    INDEX
    Explanations

    phrases related to emotions, particularly relief and elation

    oai_token-act-pair · gpt-3.5-turbo

    expressions of relief or positive emotional responses

    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
    oln
    -0.70
    lay
    -0.66
    inates
    -0.65
    rf
    -0.64
    eworks
    -0.63
    orig
    -0.63
    neau
    -0.62
    inances
    -0.61
     waivers
    -0.60
    method
    -0.60
    POSITIVE LOGITS
     exclaim
    0.85
     anticipation
    0.82
     awaiting
    0.79
     disbelief
    0.78
     wondering
    0.78
     indignation
    0.77
     recalling
    0.77
     ashamed
    0.74
     agony
    0.74
     exhaustion
    0.73
    Activations Density 0.277%

    No Known Activations