© 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. 22677
    Prev
    Next
    INDEX
    Explanations

    file paths or directories in a programming context

    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
    508
    +0.17
    0.9%
    207
    +0.14
    0.8%
    200
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    82
    +0.17
    0.02
    59
    +0.14
    -0.01
    92
    +0.12
    0.02
    Negative Logits
    áĢ¯
    -1.77
    áĢ¬
    -1.68
    rival
    -1.63
    amines
    -1.62
     ];
    -1.56
    romycin
    -1.48
     ],
    -1.45
    ünd
    -1.45
    arest
    -1.42
    este
    -1.42
    POSITIVE LOGITS
    idade
    1.79
    ity
    1.73
    imits
    1.69
    ians
    1.68
     atmosphere
    1.60
    ITY
    1.58
    apine
    1.50
     Parenthood
    1.50
     kid
    1.49
     adults
    1.49
    Activations Density 1.562%

    No Known Activations