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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 25825
    Prev
    Next
    INDEX
    Explanations

    overarching themes related to licenses and legal agreements

    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
    468
    +0.12
    0.7%
    376
    +0.11
    0.6%
    223
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    376
    +0.12
    0.04
    456
    +0.11
    0.02
    386
    +0.10
    0.02
    Negative Logits
    '));
    -1.64
    '))
    -1.63
    rap
    -1.51
    between
    -1.51
     between
    -1.50
     Your
    -1.49
    "));
    -1.48
     direction
    -1.47
     resulting
    -1.46
    ear
    -1.46
    POSITIVE LOGITS
    ¾
    2.21
    ĵ
    2.07
    ·¸
    2.01
    Ļ
    1.86
    ł
    1.85
    Ĭ
    1.82
    «
    1.80
    Īĺ
    1.80
    Ń
    1.79
    ī
    1.76
    Activations Density 0.167%

    No Known Activations