© 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. 29860
    Prev
    Next
    INDEX
    Explanations

    references to the mathematical concept of "axes."

    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
    310
    +0.14
    0.8%
    32
    +0.11
    0.7%
    320
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    310
    +0.14
    0.03
    264
    +0.11
    0.02
    320
    +0.10
    0.02
    Negative Logits
    utz
    -1.58
     then
    -1.48
     suppose
    -1.44
    nt
    -1.43
     else
    -1.41
    upon
    -1.40
     Caption
    -1.38
     any
    -1.35
     stomach
    -1.35
     among
    -1.34
    POSITIVE LOGITS
    bian
    2.01
    eries
    1.92
    ophone
    1.63
    eur
    1.63
    golang
    1.62
    iom
    1.60
    press
    1.60
    esan
    1.55
    borg
    1.54
    etine
    1.54
    Activations Density 0.995%

    No Known Activations