© 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. 30292
    Prev
    Next
    INDEX
    Explanations

    repeated instances of specific phrase patterns or structures

    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
    495
    +0.11
    0.6%
    115
    +0.11
    0.6%
    322
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    322
    +0.11
    0.05
    495
    +0.11
    0.04
    261
    +0.11
    0.04
    Negative Logits
    "}](#
    -1.72
     AFFIRMED
    -1.52
    ostic
    -1.49
    clud
    -1.46
    creen
    -1.45
    -1.44
    -1.43
    -1.41
    -1.39
    -1.32
    POSITIVE LOGITS
    fully
    1.64
    ável
    1.52
    {|
    1.48
    ½
    1.47
    ¬
    1.47
    ()</
    1.44
    tails
    1.40
    ÅĽ
    1.39
    adoc
    1.35
    ”,
    1.34
    Activations Density 0.033%

    No Known Activations