© 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. 22472
    Prev
    Next
    INDEX
    Explanations

    phrases indicating the absence of warranty or guarantees

    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
    426
    +0.10
    0.5%
    331
    +0.10
    0.5%
    349
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    414
    +0.10
    0.01
    250
    +0.10
    0.01
    352
    +0.10
    0.01
    Negative Logits
     Redistributions
    -1.63
     prol
    -1.54
    qq
    -1.48
    ql
    -1.44
     sole
    -1.40
     License
    -1.37
    amba
    -1.35
     heels
    -1.34
    oul
    -1.34
    !\
    -1.33
    POSITIVE LOGITS
    âĢij
    1.62
    IU
    1.51
     IU
    1.51
     Acute
    1.50
    AFP
    1.41
     Photo
    1.40
     Industries
    1.37
    place
    1.36
    wered
    1.35
    fold
    1.35
    Activations Density 0.083%

    No Known Activations