© 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. 28592
    Prev
    Next
    INDEX
    Explanations

    instances of a specific year, particularly 2001

    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
    250
    +0.16
    0.9%
    110
    +0.15
    0.8%
    44
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    110
    +0.16
    0.03
    250
    +0.15
    0.03
    44
    +0.12
    0.02
    Negative Logits
     behold
    -1.74
     answer
    -1.62
     close
    -1.57
     fair
    -1.57
     trouble
    -1.56
     comment
    -1.55
    ights
    -1.54
     sheaf
    -1.54
     power
    -1.54
     suspicion
    -1.53
    POSITIVE LOGITS
    icolor
    1.95
    ி
    1.62
    ienn
    1.58
    à¯ģ
    1.58
    icol
    1.53
    olecule
    1.48
    iom
    1.47
    Align
    1.44
    Cells
    1.44
    EventArgs
    1.42
    Activations Density 0.009%

    No Known Activations