© 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. 0-MLP-SM
    11. 29751
    Prev
    Next
    INDEX
    Explanations

    references to documentation or guidelines

    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
    167
    +0.14
    0.8%
    53
    +0.11
    0.6%
    353
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    354
    +0.14
    0.07
    51
    +0.11
    0.05
    188
    +0.11
    0.06
    Negative Logits
    Ŀ
    -3.06
    ·¸
    -2.80
    IJ
    -2.76
    ²
    -2.71
    ±
    -2.62
    Īĺ
    -2.58
    »¿
    -2.57
    ½
    -2.50
    ¶
    -2.46
    ħ
    -2.46
    POSITIVE LOGITS
    TP
    1.46
     drain
    1.45
    Empty
    1.41
    thy
    1.40
    tet
    1.39
    Wrap
    1.37
    tu
    1.37
    dered
    1.35
    -$
    1.34
    zer
    1.28
    Activations Density 0.038%

    No Known Activations