© 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. 26566
    Prev
    Next
    INDEX
    Explanations

    references to significant works or terms in the context of art and culture

    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
    480
    +0.12
    0.7%
    35
    +0.12
    0.7%
    229
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    203
    +0.12
    0.49
    56
    +0.12
    0.18
    258
    +0.11
    0.43
    Negative Logits
    ocol
    -1.73
    umbo
    -1.54
     replication
    -1.53
    OUR
    -1.52
     Conclusions
    -1.52
     deletion
    -1.49
    oke
    -1.47
    IGNED
    -1.46
     reorganization
    -1.44
    amazon
    -1.44
    POSITIVE LOGITS
    ĥ½
    5.19
    ij
    5.17
    Ļª
    5.14
    ĥ
    5.04
    ¾
    4.96
    Ģ
    4.79
    Ĵ
    4.74
    ĭ
    4.73
    »¿
    4.71
    Į
    4.67
    Activations Density 6.714%

    No Known Activations