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

    Neuronpedia

    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. 27805
    Prev
    Next
    INDEX
    Explanations

    statements related to assertions in test cases

    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
    148
    +0.12
    0.7%
    391
    +0.11
    0.6%
    248
    +0.09
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    204
    +0.12
    0.02
    101
    +0.11
    0.02
    391
    +0.09
    0.02
    Negative Logits
    ĵ
    -2.04
    kinase
    -1.80
    zzle
    -1.75
    ))**
    -1.74
    ,}
    -1.71
    ife
    -1.69
    ))**(
    -1.63
    chten
    -1.60
    ))**(-
    -1.59
    $}
    -1.58
    POSITIVE LOGITS
     opera
    1.82
     pitches
    1.66
     swings
    1.58
    orious
    1.55
     songs
    1.53
     apparatus
    1.48
    fires
    1.46
    fire
    1.45
     surroundings
    1.43
    orate
    1.43
    Activations Density 0.840%

    No Known Activations