© 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. 25301
    Prev
    Next
    INDEX
    Explanations

    numeric values and comparative statistics

    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
    23
    +0.17
    1.0%
    298
    +0.14
    0.8%
    210
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    231
    +0.17
    0.03
    410
    +0.14
    0.02
    414
    +0.13
    0.01
    Negative Logits
     underestimated
    -2.11
     overest
    -1.78
    »¿
    -1.60
    ¥
    -1.59
    verte
    -1.58
     \>
    -1.58
     underestimate
    -1.56
     asympt
    -1.55
     âī¤
    -1.47
     adequately
    -1.47
    POSITIVE LOGITS
     love
    1.56
    dev
    1.46
     commits
    1.44
     jealousy
    1.40
     LOVE
    1.39
     rage
    1.37
     voy
    1.37
    orned
    1.35
     commerce
    1.35
    love
    1.34
    Activations Density 0.258%

    No Known Activations