© 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. 2-MLP-SM
    11. 23997
    Prev
    Next
    INDEX
    Explanations

    occurrences of package declarations and import statements in code

    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
    307
    +0.15
    0.8%
    49
    +0.14
    0.8%
    364
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    307
    +0.15
    0.03
    364
    +0.14
    0.04
    421
    +0.11
    0.04
    Negative Logits
    iph
    -2.02
    ()).
    -1.77
    )^[@
    -1.74
    ());
    -1.67
    ())
    -1.63
    ').
    -1.62
    ')
    -1.59
    ){#
    -1.57
    [])
    -1.56
    '>
    -1.56
    POSITIVE LOGITS
    ĻĤ
    3.99
    ¿½
    3.87
    Ĥ¬
    3.42
    ģ
    3.40
    ħ
    3.33
    į
    3.32
    Ĭ
    3.32
    Īĺ
    3.25
    ¤
    3.13
    ĵ
    3.10
    Activations Density 0.072%

    No Known Activations