© 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. 23676
    Prev
    Next
    INDEX
    Explanations

    occurrences of HTML script tags and related attributes

    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
    422
    +0.13
    0.7%
    352
    +0.10
    0.5%
    57
    +0.09
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    422
    +0.13
    0.02
    316
    +0.10
    0.02
    352
    +0.09
    0.01
    Negative Logits
    Į
    -1.72
    ľĵ
    -1.70
    ãĤĩ
    -1.68
    áĢ¯
    -1.61
    ãģ¾ãģĽãĤĵ
    -1.58
    ======
    -1.56
    ĨĴ
    -1.55
    ãĤĥ
    -1.55
    ãģ¾ãģĽ
    -1.52
    ëĭĪëĭ¤
    -1.51
    POSITIVE LOGITS
     onward
    1.58
     onwards
    1.56
     colony
    1.45
     colonies
    1.42
    velopment
    1.36
     leagues
    1.35
     kingdom
    1.33
     deductions
    1.33
     countries
    1.32
    LEY
    1.31
    Activations Density 0.081%

    No Known Activations