© 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. 26970
    Prev
    Next
    INDEX
    Explanations

    references to specific connections or relationships 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/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
    118
    +0.12
    0.6%
    500
    +0.11
    0.6%
    455
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    455
    +0.12
    0.05
    118
    +0.11
    0.05
    255
    +0.11
    0.05
    Negative Logits
    Ļ
    -2.24
    ħ
    -2.17
    ĻĤ
    -2.17
    º
    -2.14
    ª
    -2.11
    ŀ
    -2.03
    ³
    -1.98
    Ĺ
    -1.97
    §
    -1.91
    ·¸
    -1.88
    POSITIVE LOGITS
    \])]{}
    1.75
    ^](#
    1.74
    ]{})
    1.67
    results
    1.66
    ]{}
    1.65
    zero
    1.51
    opia
    1.47
     ‘
    1.47
    plots
    1.46
    """
    1.44
    Activations Density 0.179%

    No Known Activations