© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 27669
    Prev
    Next
    INDEX
    Explanations

    quotes or dialogue markers in the text

    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
    279
    +0.12
    0.6%
    287
    +0.11
    0.6%
    76
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    188
    +0.12
    0.17
    154
    +0.11
    0.14
    486
    +0.11
    0.14
    Negative Logits
    ³
    -3.45
    ½
    -3.27
    ĥ½
    -3.20
    Ĥ
    -3.19
    Ħ
    -3.14
      ↵
    -3.08
    ↵
    -3.08
              ↵
    -3.08
    ↵  ↵
    -3.08
    ↵
    -3.08
    POSITIVE LOGITS
     itself
    1.62
     miser
    1.43
    gger
    1.37
    its
    1.35
    taire
    1.35
    me
    1.33
    ark
    1.32
     founded
    1.29
     stool
    1.28
    blic
    1.28
    Activations Density 0.411%

    No Known Activations