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. 4-RES-JB
    6. 3768
    Prev
    Next
    INDEX
    Explanations

    instances of the word "feeling" along with its intensity

    oai_token-act-pair · gpt-3.5-turbo

    references to emotions or feelings

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

    No Comments

    Negative Logits
    lishing
    -0.76
    annis
    -0.68
    photos
    -0.67
    itures
    -0.66
    sites
    -0.63
    reek
    -0.63
    heid
    -0.63
     Springer
    -0.63
    ammers
    -0.62
    hire
    -0.61
    POSITIVE LOGITS
     vibrations
    0.94
     compelled
    0.85
     uneasy
    0.83
     comfortable
    0.81
     sensations
    0.81
    igue
    0.78
    uated
    0.73
     nostalgic
    0.73
     vibration
    0.72
     uncomfortable
    0.72
    Activations Density 0.021%

    No Known Activations