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. 6-RES-JB
    6. 23684
    Prev
    Next
    INDEX
    Explanations

    emotionally charged and descriptive words and phrases

    oai_token-act-pair · gpt-3.5-turbo

    emotional moments or expressions in storytelling

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ospons
    -0.84
    osponsors
    -0.73
    eligible
    -0.72
    endment
    -0.71
     Certification
    -0.70
    backer
    -0.68
    "))
    -0.68
    Prior
    -0.67
    ļéĨĴ
    -0.64
    Federal
    -0.64
    POSITIVE LOGITS
     pleasures
    1.04
     melancholy
    1.00
     thrill
    0.95
     palpable
    0.91
     exhilar
    0.91
     melanch
    0.91
     throb
    0.91
     deft
    0.90
     revel
    0.90
     poetic
    0.89
    Activations Density 1.616%

    No Known Activations