© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 22502
    Prev
    Next
    INDEX
    Explanations

    references to participation or involvement in activities or events

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Neuron Alignment
    Index
    Value
    % of L₁
    500
    +0.15
    0.8%
    155
    +0.14
    0.8%
    297
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    155
    +0.15
    0.04
    297
    +0.14
    0.03
    500
    +0.12
    0.02
    Negative Logits
    uration
    -1.53
    achine
    -1.50
    oit
    -1.46
    ader
    -1.41
    dule
    -1.40
    imization
    -1.31
     sap
    -1.30
     abras
    -1.29
    ctin
    -1.28
    STEM
    -1.28
    POSITIVE LOGITS
    »¿
    2.58
    Ģ
    1.84
    Ħ
    1.72
    ®
    1.68
    lies
    1.65
    ħ
    1.63
    AFFIRMED
    1.59
    lessly
    1.58
    ķ
    1.55
    pires
    1.51
    Activations Density 0.136%

    No Known Activations