© 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. 28793
    Prev
    Next
    INDEX
    Explanations

    the name "Kir" and possibly related mentions or variations of it

    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
    369
    +0.24
    1.4%
    59
    +0.16
    1.0%
    111
    +0.13
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    59
    +0.24
    0.01
    55
    +0.16
    0.01
    111
    +0.13
    0.01
    Negative Logits
    semin
    -1.68
    oston
    -1.63
    "?"
    -1.56
    attention
    -1.52
     her
    -1.52
    plasia
    -1.51
    noreply
    -1.49
    ofib
    -1.44
    ftware
    -1.44
    eb
    -1.41
    POSITIVE LOGITS
    ings
    1.69
     (,
    1.57
    (@
    1.51
     unless
    1.48
    wan
    1.48
    genstein
    1.47
     equivalents
    1.43
     ()
    1.41
    aho
    1.39
    rored
    1.37
    Activations Density 0.007%

    No Known Activations