© 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. 30469
    Prev
    Next
    INDEX
    Explanations

    instances of actions or decisions made without specific intention or planning

    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
    376
    +0.20
    1.1%
    170
    +0.13
    0.7%
    33
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    170
    +0.20
    0.01
    33
    +0.13
    0.01
    339
    +0.12
    0.01
    Negative Logits
    rie
    -1.58
    iless
    -1.56
    ELD
    -1.50
     promise
    -1.48
    ĸ´
    -1.45
     greatest
    -1.41
    Ļª
    -1.38
    ĥ
    -1.36
    tico
    -1.36
     most
    -1.36
    POSITIVE LOGITS
    ball
    1.59
    nis
    1.52
    issions
    1.51
    ovir
    1.49
    burg
    1.46
    tum
    1.44
    ement
    1.42
     Pence
    1.38
    genstein
    1.37
    blr
    1.36
    Activations Density 0.009%

    No Known Activations