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. 17181
    Prev
    Next
    INDEX
    Explanations

    words related to intense emotions and impactful experiences

    oai_token-act-pair · gpt-3.5-turbo

    intensifiers related to emotional or impactful experiences

    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
    ulia
    -0.80
    culosis
    -0.76
    ropolis
    -0.74
     Intake
    -0.74
     Estimates
    -0.74
    Stack
    -0.72
     Inventory
    -0.71
    cius
    -0.70
    orsi
    -0.70
    prus
    -0.69
    POSITIVE LOGITS
     hilarious
    1.52
     exciting
    1.49
     interesting
    1.48
     fascinating
    1.43
     thrilling
    1.40
     funny
    1.39
     heartbreaking
    1.39
     scary
    1.37
     poignant
    1.36
     amusing
    1.36
    Activations Density 0.316%

    No Known Activations