© 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. 26727
    Prev
    Next
    INDEX
    Explanations

    functions related to error handling or conditional checks in programming

    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
    370
    +0.17
    0.9%
    61
    +0.14
    0.7%
    476
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    322
    +0.17
    0.05
    495
    +0.14
    0.04
    261
    +0.13
    0.04
    Negative Logits
    lessly
    -2.15
    edly
    -1.76
    lights
    -1.66
    agles
    -1.63
    ât
    -1.57
    à§ĩ
    -1.52
    lay
    -1.51
    chair
    -1.50
    hole
    -1.47
    arthy
    -1.46
    POSITIVE LOGITS
     follows
    1.73
    nes
    1.59
     want
    1.55
    thens
    1.54
    IX
    1.51
    ighting
    1.47
    ission
    1.46
    orious
    1.43
    ix
    1.41
     wish
    1.40
    Activations Density 0.033%

    No Known Activations