© 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. 0-MLP-SM
    11. 25265
    Prev
    Next
    INDEX
    Explanations

    references to the present time

    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
    156
    +0.24
    1.4%
    376
    +0.14
    0.8%
    257
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    257
    +0.24
    0.01
    94
    +0.14
    0.01
    89
    +0.13
    0.01
    Negative Logits
    ige
    -1.51
    etus
    -1.48
    ´
    -1.44
    rier
    -1.33
     balls
    -1.29
    leg
    -1.28
    ikh
    -1.26
    iki
    -1.26
    Ĥ¬
    -1.26
    ħ
    -1.25
    POSITIVE LOGITS
    "}](#
    1.84
    ontal
    1.81
    chitz
    1.59
    orph
    1.39
    ORDER
    1.36
    wealth
    1.35
     sizeof
    1.33
     quoting
    1.32
    dial
    1.31
    orrow
    1.30
    Activations Density 0.029%

    No Known Activations