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. 3-RES-JB
    6. 19653
    Prev
    Next
    INDEX
    Explanations

    references to the moon Europa

    oai_token-act-pair · gpt-3.5-turbo

    mentions of "Europa," particularly in scientific or entertainment contexts

    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
    enegger
    -1.12
    allow
    -0.79
    orses
    -0.74
    ////////////////
    -0.73
    reads
    -0.72
    smith
    -0.72
    nu
    -0.72
    writers
    -0.72
    yang
    -0.72
    edo
    -0.72
    POSITIVE LOGITS
     Europa
    1.17
    lehem
    0.72
     League
    0.70
     strugg
    0.70
     Universal
    0.67
     Knot
    0.66
     goalkeeper
    0.64
     unlaw
    0.64
    iosyn
    0.64
     Cru
    0.63
    Activations Density 0.008%

    No Known Activations