© 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. 23878
    Prev
    Next
    INDEX
    Explanations

    terms related to health and medical research

    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
    66
    +0.15
    0.8%
    396
    +0.12
    0.7%
    211
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    4
    +0.15
    0.37
    396
    +0.12
    0.37
    49
    +0.12
    0.32
    Negative Logits
    £
    -2.31
    Ļ
    -1.79
    ı
    -1.76
    ĨĴ
    -1.74
    Ľ
    -1.73
    °
    -1.70
    ½
    -1.67
    ģ
    -1.66
    »
    -1.64
    ĥ½
    -1.58
    POSITIVE LOGITS
    ements
    1.61
    )—
    1.57
    ftware
    1.50
    ños
    1.48
    versions
    1.44
    tti
    1.44
    lasses
    1.43
    esp
    1.41
    rios
    1.40
    gon
    1.39
    Activations Density 3.969%

    No Known Activations