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. 0-RES-JB
    6. 975
    Prev
    Next
    INDEX
    Explanations

    references or mentions of planets

    oai_token-act-pair · gpt-3.5-turbo

    references to planets and planetary themes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Cases
    -0.70
     Sweeney
    -0.69
    aid
    -0.68
    cases
    -0.65
    Interested
    -0.65
     Examples
    -0.65
     Reps
    -0.62
    ricks
    -0.61
    Statistics
    -0.60
     Cork
    -0.60
    POSITIVE LOGITS
     planet
    3.68
    planet
    2.49
     Planet
    2.42
    Planet
    2.22
     planets
    2.21
     planetary
    2.00
     Earth
    1.76
    eworld
    1.74
     continent
    1.73
     galaxy
    1.66
    Activations Density 0.018%

    No Known Activations