© 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. 2-MLP-SM
    11. 26117
    Prev
    Next
    INDEX
    Explanations

    references to "pieces" or components of various items or concepts

    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
    107
    +0.14
    0.8%
    312
    +0.12
    0.7%
    26
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    107
    +0.14
    0.03
    55
    +0.12
    0.03
    120
    +0.11
    0.05
    Negative Logits
    .]
    -2.04
    "}](#
    -2.01
    )].
    -1.82
    ."[
    -1.79
    ]."
    -1.77
    *]{}.
    -1.72
    "].
    -1.68
    !).
    -1.67
    iNdEx
    -1.65
    .''
    -1.64
    POSITIVE LOGITS
    «
    2.12
    Ĥ¬
    1.87
    į
    1.86
    ĭ
    1.70
    ¥
    1.69
    Ģ
    1.69
    ł
    1.61
      ↵
    1.57
    1.57
    <|outofrange|>
    1.57
    Activations Density 0.686%

    No Known Activations