© 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
    2. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    3. Pythia-70M-Deduped
    4. MLP Post
    5. 2-MLP-SM
    6. 23089
    Prev
    Next
    INDEX
    Explanations

    code that contains export statements

    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
    159
    +0.12
    0.6%
    185
    +0.10
    0.6%
    511
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    421
    +0.12
    0.02
    68
    +0.10
    0.01
    383
    +0.10
    0.02
    Negative Logits
     smartphones
    -1.49
     adults
    -1.43
     Jesus
    -1.42
    heed
    -1.38
     mobile
    -1.38
     Europeans
    -1.36
     Africans
    -1.35
     office
    -1.34
     [<
    -1.33
     iPod
    -1.32
    POSITIVE LOGITS
    ī
    4.75
    Ĭ
    4.47
    ¡
    4.46
    ĩ
    4.38
    ħ
    4.28
    ı
    4.20
    IJ
    4.18
    »
    4.14
    Į
    4.12
    Īĺ
    4.11
    Activations Density 0.171%

    No Known Activations