© 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. 24276
    Prev
    Next
    INDEX
    Explanations

    URLs and web links

    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
    156
    +0.23
    1.3%
    509
    +0.12
    0.6%
    275
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    59
    +0.23
    -0.02
    275
    +0.12
    -0.03
    86
    +0.10
    0.03
    Negative Logits
    alus
    -1.85
    aliana
    -1.80
     broadcasts
    -1.66
     bells
    -1.56
     displayed
    -1.56
    youtube
    -1.56
    blic
    -1.54
     Live
    -1.53
    bell
    -1.52
    ouds
    -1.46
    POSITIVE LOGITS
    ĥ
    4.20
    IJ
    4.05
    ¼
    4.01
    Ĥ
    3.97
    °
    3.92
    Ļª
    3.79
    Ĭ
    3.76
    İ
    3.73
    ĭ
    3.71
    ħ
    3.65
    Activations Density 1.973%

    No Known Activations