© 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. 29104
    Prev
    Next
    INDEX
    Explanations

    instances of simplicity or ease in tasks or processes

    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
    397
    +0.12
    0.7%
    458
    +0.12
    0.7%
    438
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    452
    +0.12
    0.05
    397
    +0.12
    0.04
    400
    +0.12
    0.04
    Negative Logits
    smallcaps
    -1.68
    UAL
    -1.54
     glare
    -1.51
    riel
    -1.51
    eLife
    -1.49
     Studies
    -1.43
    uality
    -1.42
     Species
    -1.36
    anese
    -1.36
     Team
    -1.32
    POSITIVE LOGITS
    going
    1.81
    pered
    1.74
    ioned
    1.67
    itud
    1.61
     enough
    1.51
    reich
    1.51
    ety
    1.47
    unto
    1.47
    tery
    1.47
    market
    1.46
    Activations Density 0.585%

    No Known Activations