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. 3-RES-JB
    6. 1120
    Prev
    Next
    INDEX
    Explanations

    chemical compounds related to cyclic structures

    oai_token-act-pair · gpt-3.5-turbo

    mentions of chemical compounds and specific entities related to cycling or Catalonia

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    UGE
    -0.85
    IELD
    -0.82
     Zucker
    -0.70
    ELL
    -0.68
     Ellen
    -0.62
     Bots
    -0.62
     Korea
    -0.62
     Cheong
    -0.62
     Cookie
    -0.61
     Orion
    -0.60
    POSITIVE LOGITS
    cycl
    1.01
    ical
    1.00
    icals
    0.97
    icles
    0.91
    ophone
    0.88
    icism
    0.83
    icle
    0.81
    olit
    0.80
    iste
    0.79
    acy
    0.79
    Activations Density 0.007%

    No Known Activations