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. 0-RES-JB
    6. 992
    Prev
    Next
    INDEX
    Explanations

    the word "happily" paired with various verbs expressing positive actions or outcomes

    oai_token-act-pair · gpt-3.5-turbo

    expressions of happiness or positive emotional states

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    entin
    -0.65
    resa
    -0.63
    cius
    -0.63
    rez
    -0.62
     AM
    -0.62
    impact
    -0.59
     Investigator
    -0.59
     CT
    -0.58
    ussion
    -0.58
    án
    -0.58
    POSITIVE LOGITS
     happily
    3.36
     gladly
    2.95
     willingly
    1.99
     eagerly
    1.77
     enthusiastically
    1.61
     reluctantly
    1.48
     dearly
    1.34
     patiently
    1.34
     silently
    1.22
     effortlessly
    1.22
    Activations Density 0.015%

    No Known Activations