© 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. 26305
    Prev
    Next
    INDEX
    Explanations

    references to friendships

    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
    376
    +0.19
    1.1%
    156
    +0.17
    1.0%
    270
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    270
    +0.19
    0.01
    268
    +0.17
    0.01
    185
    +0.12
    0.01
    Negative Logits
    ĵ
    -3.42
    ©
    -3.41
    ı
    -3.35
    §
    -3.30
    ¯
    -3.24
    ĩ
    -3.06
    ¸
    -3.05
    Ĺ
    -2.95
    Ĵ
    -2.91
    ľ
    -2.91
    POSITIVE LOGITS
    manship
    2.08
    forge
    1.82
    hip
    1.72
    hof
    1.72
    hold
    1.72
    sheet
    1.71
    tree
    1.71
    pieces
    1.70
    fficients
    1.70
    burg
    1.70
    Activations Density 0.009%

    No Known Activations