© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 22629
    Prev
    Next
    INDEX
    Explanations

    references to people and community engagement

    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
    98
    +0.14
    0.8%
    211
    +0.13
    0.8%
    4
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    211
    +0.14
    0.05
    401
    +0.13
    0.04
    95
    +0.12
    0.03
    Negative Logits
    IJ
    -1.56
     respecting
    -1.48
    makers
    -1.47
    Īĺ
    -1.45
    ļ
    -1.44
    Ĭ
    -1.42
    Ģ
    -1.41
    Ł
    -1.39
    ©
    -1.37
     queen
    -1.36
    POSITIVE LOGITS
    alc
    1.52
    ried
    1.52
    quire
    1.51
    ithub
    1.49
    enso
    1.45
    noop
    1.37
    googleapis
    1.35
     Archives
    1.34
    lee
    1.33
    Selected
    1.32
    Activations Density 0.291%

    No Known Activations