© 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 EvalsExportsAPI 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. 24612
    Prev
    Next
    INDEX
    Explanations

    statistical data related to age groups

    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
    497
    +0.15
    0.9%
    231
    +0.13
    0.7%
    271
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    497
    +0.15
    0.02
    231
    +0.13
    0.08
    113
    +0.13
    0.09
    Negative Logits
    chter
    -1.43
    onset
    -1.42
    plit
    -1.41
    ining
    -1.40
    .[@
    -1.37
     ranged
    -1.35
     racket
    -1.34
    âĢĤ
    -1.34
    erald
    -1.33
    \)
    -1.28
    POSITIVE LOGITS
    ±
    1.61
    atar
    1.55
    secret
    1.50
    OnClickListener
    1.49
    friend
    1.48
    ¶
    1.47
     instance
    1.43
    avascript
    1.42
    ļ
    1.42
     messenger
    1.40
    Activations Density 1.105%

    No Known Activations