© 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 EvalsExportsAPI 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. 28350
    Prev
    Next
    INDEX
    Explanations

    references to data frames and their manipulation

    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
    182
    +0.17
    1.0%
    369
    +0.12
    0.7%
    63
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    182
    +0.17
    0.01
    63
    +0.12
    0.01
    320
    +0.12
    0.01
    Negative Logits
    ı
    -2.05
    ¿
    -1.86
    Ļª
    -1.78
    ĵ
    -1.75
    ubottu
    -1.72
    -1.67
    -1.67
     ↵
    -1.67
    ↵
    -1.67
    -1.67
    POSITIVE LOGITS
    illac
    1.58
    ressor
    1.53
    Rptr
    1.51
    ipline
    1.50
     opinion
    1.49
    80211
    1.49
    ilt
    1.46
    ÃŃo
    1.44
    reed
    1.40
    ritz
    1.37
    Activations Density 0.021%

    No Known Activations