© 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. 0-MLP-SM
    11. 29656
    Prev
    Next
    INDEX
    Explanations

    phrases indicating direction or intention

    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/0-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.0.hook_mlp_out
    Hook Layer
    0
    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
    357
    +0.12
    0.7%
    303
    +0.11
    0.6%
    424
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    69
    +0.12
    0.38
    151
    +0.11
    0.31
    434
    +0.11
    0.30
    Negative Logits
    ault
    -1.57
    igens
    -1.57
    âĢij
    -1.50
    QUE
    -1.49
    ders
    -1.47
    inois
    -1.46
    iels
    -1.43
     innocence
    -1.42
    th
    -1.41
    ricular
    -1.40
    POSITIVE LOGITS
    ¿½
    2.47
    ľĵ
    2.35
    Ļ
    2.29
    Ī
    2.27
    Īĺ
    2.25
    ĥ½
    2.16
    Į
    2.10
    Ł
    2.05
    »
    2.03
    ¢
    1.99
    Activations Density 1.638%

    No Known Activations