© 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. 23574
    Prev
    Next
    INDEX
    Explanations

    sources or references related to health and social issues

    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
    149
    +0.11
    0.6%
    331
    +0.11
    0.6%
    65
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    149
    +0.11
    0.04
    56
    +0.11
    0.06
    422
    +0.11
    0.04
    Negative Logits
    ³
    -4.54
    Ĩ
    -4.30
    ¢
    -4.30
    Ń
    -4.21
    ¾
    -4.13
    ĥ
    -4.05
    ī
    -4.05
    ĭ
    -4.04
    Ī
    -4.01
    §
    -4.01
    POSITIVE LOGITS
    fered
    1.45
    ousand
    1.45
    orno
    1.45
    ))).
    1.38
    isse
    1.27
    bons
    1.27
    inib
    1.26
    izable
    1.26
    omyces
    1.23
    ideo
    1.22
    Activations Density 0.438%

    No Known Activations