© 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. 2-MLP-SM
    11. 23566
    Prev
    Next
    INDEX
    Explanations

    repeated mentions of "auto" in various contexts

    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/2-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.2.hook_mlp_out
    Hook Layer
    2
    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
    182
    +0.14
    0.8%
    317
    +0.14
    0.7%
    84
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    317
    +0.14
    0.03
    23
    +0.14
    0.01
    56
    +0.12
    0.03
    Negative Logits
    §
    -4.53
    <|outofrange|>
    -4.42
    ↵
    -4.42
    -4.42
    ↵
    -4.42
              ↵
    -4.42
    -4.42
    -4.42
    ↵↵
    -4.42
      ↵
    -4.42
    POSITIVE LOGITS
    raf
    1.43
    TRODUCTION
    1.41
     precedent
    1.40
     APPEALS
    1.33
    needed
    1.31
    ants
    1.31
    ONE
    1.30
    aligned
    1.28
    rox
    1.25
     future
    1.25
    Activations Density 0.373%

    No Known Activations