© 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. 25886
    Prev
    Next
    INDEX
    Explanations

    reports or mentions of current events

    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
    505
    +0.15
    0.8%
    490
    +0.11
    0.6%
    365
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    505
    +0.15
    0.04
    229
    +0.11
    0.03
    490
    +0.11
    0.03
    Negative Logits
    ĭ
    -2.90
    §
    -2.69
    ¤
    -2.45
    Ī
    -2.41
    Į
    -2.40
    ĥ½
    -2.40
    IJ
    -2.40
    ¿
    -2.29
    º
    -2.26
    ī
    -2.25
    POSITIVE LOGITS
    stand
    1.74
    wick
    1.74
    match
    1.69
    icles
    1.64
    úblic
    1.63
    gered
    1.61
    letter
    1.61
    lang
    1.59
    ios
    1.56
    hth
    1.55
    Activations Density 0.117%

    No Known Activations