© 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. 0-MLP-SM
    11. 30982
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate relevance or importance

    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
    156
    +0.24
    1.4%
    376
    +0.19
    1.1%
    110
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    110
    +0.24
    0.02
    265
    +0.19
    0.02
    372
    +0.14
    0.02
    Negative Logits
    astern
    -1.68
    idegger
    -1.63
    orian
    -1.44
    ussi
    -1.43
    heimer
    -1.42
    enson
    -1.42
    called
    -1.41
    ctrine
    -1.39
     Surviv
    -1.35
    ureus
    -1.34
    POSITIVE LOGITS
     pieces
    1.78
    ¢
    1.63
    º
    1.60
    ities
    1.57
     pic
    1.51
     interests
    1.44
     gaps
    1.42
     roles
    1.41
    ?!
    1.37
    ences
    1.37
    Activations Density 0.044%

    No Known Activations