© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    5. Pythia-70M-Deduped
    7. MLP Post
    9. 0-MLP-SM
    11. 30869
    Prev
    Next
    INDEX
    Explanations

    references to Halloween

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    ctigges/pythia-70m-deduped__mlp-sm_processed/0-mlp-sm
    Prompts (Dashboard)
    32,768 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    32,768
    Data Type
    torch.float32
    Hook Name
    blocks.0.hook_mlp_out
    Hook Layer
    0
    Architecture
    standard
    Context Size
    128
    Dataset
    EleutherAI/the_pile_deduplicated
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    156
    +0.24
    1.4%
    71
    +0.14
    0.8%
    115
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1
    +0.24
    0.02
    71
    +0.14
    0.01
    397
    +0.13
    0.01
    Negative Logits
    Ŀ
    -4.83
    ı
    -4.82
    ¢
    -4.80
    į
    -4.80
    ¯
    -4.65
                ↵
    -4.63
    -4.63
    -4.63
    -4.63
    ↵
    -4.63
    POSITIVE LOGITS
    opan
    1.64
    itic
    1.57
     anthem
    1.55
     festivals
    1.43
    ++,
    1.43
     rituals
    1.42
    vre
    1.41
     costumes
    1.40
    fors
    1.40
     celebrations
    1.40
    Activations Density 0.031%

    No Known Activations