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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 3692
    Prev
    Next
    INDEX
    Explanations

    positive emotional descriptors

    oai_token-act-pair · gpt-3.5-turbo

    emotive adjectives that convey strong feelings or reactions

    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
    rongh
    -0.77
    è£
    -0.67
    arta
    -0.67
    asus
    -0.62
    Rated
    -0.62
    along
    -0.61
    haar
    -0.61
    edIn
    -0.60
    resp
    -0.60
    ongh
    -0.60
    POSITIVE LOGITS
     seeing
    1.18
     how
    1.01
     knowing
    0.95
     watching
    0.92
     when
    0.87
     hearing
    0.86
     coincidence
    0.82
     imagining
    0.80
     considering
    0.79
     witnessing
    0.77
    Activations Density 0.147%

    No Known Activations