© 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. 30834
    Prev
    Next
    INDEX
    Explanations

    formatted elements or collections in code

    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
    478
    +0.17
    1.0%
    91
    +0.12
    0.7%
    274
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    91
    +0.17
    0.02
    55
    +0.12
    0.02
    124
    +0.11
    0.02
    Negative Logits
    Ł
    -1.80
    Ń
    -1.57
    ±
    -1.48
    ood
    -1.47
      ↵
    -1.47
    rence
    -1.47
    -1.47
            ↵
    -1.47
    ↵↵
    -1.47
    -1.47
    POSITIVE LOGITS
    fony
    1.86
    unreadable
    1.84
    dual
    1.66
    ClCompile
    1.61
    веÑĢ
    1.56
    cyl
    1.55
    dimen
    1.53
     pockets
    1.48
    %--
    1.46
    strap
    1.40
    Activations Density 0.776%

    No Known Activations