© 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. 2-MLP-SM
    11. 23962
    Prev
    Next
    INDEX
    Explanations

    path segments and references to external files or URLs

    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
    137
    +0.14
    0.8%
    59
    +0.13
    0.7%
    177
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    59
    +0.14
    0.01
    50
    +0.13
    0.03
    269
    +0.12
    0.03
    Negative Logits
    à±ģ
    -1.98
     those
    -1.70
     donors
    -1.60
    à±į
    -1.54
    ;"
    -1.52
     background
    -1.48
    pdev
    -1.46
     \;
    -1.42
     '@
    -1.41
     these
    -1.40
    POSITIVE LOGITS
    ª
    3.20
    ľ
    3.06
    ¸
    3.03
    §
    3.01
    ¤
    2.94
    Ŀ
    2.94
    Ĵ
    2.88
    ¿½
    2.87
    ¬
    2.84
    Ĺ
    2.82
    Activations Density 1.014%

    No Known Activations