© 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 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. 25054
    Prev
    Next
    INDEX
    Explanations

    references to long-term concepts or considerations

    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
    165
    +0.12
    0.7%
    85
    +0.12
    0.7%
    167
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    94
    +0.12
    0.04
    248
    +0.12
    0.03
    417
    +0.12
    0.04
    Negative Logits
    Ļª
    -3.70
    Ĥ¬
    -3.62
    ¦
    -3.61
    ł
    -3.58
    Ļ
    -3.57
    Ĵ
    -3.54
    ĥ
    -3.53
    Ŀ
    -3.51
    ħ
    -3.51
    Ĩ
    -3.51
    POSITIVE LOGITS
    fecture
    1.42
    \|^
    1.42
    gett
    1.40
     mentally
    1.39
    ancies
    1.38
    utory
    1.35
     seriously
    1.33
     suppose
    1.32
     duties
    1.30
     why
    1.30
    Activations Density 0.508%

    No Known Activations