© 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. 24232
    Prev
    Next
    INDEX
    Explanations

    comparisons or similar things

    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
    423
    +0.14
    0.8%
    331
    +0.12
    0.7%
    111
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    423
    +0.14
    0.04
    225
    +0.12
    0.03
    331
    +0.11
    0.02
    Negative Logits
    ĻĤ
    -2.14
    ŀ
    -2.12
    Ŀ
    -1.95
    ®
    -1.77
    ĸ
    -1.69
    ļ
    -1.68
    µ
    -1.67
    Ł
    -1.65
     directions
    -1.60
    ª
    -1.60
    POSITIVE LOGITS
    esty
    1.59
    asone
    1.52
    zez
    1.52
     quo
    1.49
    rendum
    1.48
    ingale
    1.43
    ateness
    1.39
    ème
    1.36
    ↵Č
    1.36
    iance
    1.34
    Activations Density 0.173%

    No Known Activations