© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 26987
    Prev
    Next
    INDEX
    Explanations

    specific numeric codes or years within text

    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
    23
    +0.17
    1.0%
    186
    +0.14
    0.8%
    337
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    460
    +0.17
    0.02
    362
    +0.14
    0.02
    82
    +0.12
    0.02
    Negative Logits
    ij
    -3.18
    ½
    -3.07
    Ħ
    -3.05
    į
    -3.05
    «
    -3.03
    ¾
    -3.02
    Į
    -3.01
    º
    -3.01
    ¥
    -2.98
    Ń
    -2.91
    POSITIVE LOGITS
     stable
    1.55
     else
    1.43
    lain
    1.43
    inite
    1.42
     unity
    1.41
     ever
    1.41
     doubt
    1.34
    IRST
    1.33
    GFR
    1.32
    EVER
    1.32
    Activations Density 0.216%

    No Known Activations