© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    5. Pythia-70M-Deduped
    7. MLP Post
    9. 2-MLP-SM
    11. 25173
    Prev
    Next
    INDEX
    Explanations

    references to the Apache License

    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/2-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.2.hook_mlp_out
    Hook Layer
    2
    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
    23
    +0.15
    0.9%
    426
    +0.13
    0.7%
    74
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    426
    +0.15
    0.02
    8
    +0.13
    0.02
    74
    +0.12
    0.02
    Negative Logits
     lately
    -1.73
    ugu
    -1.66
    rael
    -1.62
    taient
    -1.58
    '));
    -1.54
    cdn
    -1.49
    blr
    -1.48
    ophage
    -1.47
    ypse
    -1.47
    omb
    -1.47
    POSITIVE LOGITS
    ¦
    2.08
    ¼
    1.68
    ¿½
    1.66
    Ĭ
    1.63
    IJ
    1.59
    ł
    1.56
    Ļª
    1.54
    ]:
    1.52
     Materials
    1.51
    ij
    1.44
    Activations Density 0.050%

    No Known Activations