© 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. 22610
    Prev
    Next
    INDEX
    Explanations

    phrases indicating directions or locations

    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
    419
    +0.14
    0.8%
    244
    +0.12
    0.7%
    14
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    14
    +0.14
    0.07
    404
    +0.12
    0.06
    407
    +0.12
    0.07
    Negative Logits
    iness
    -1.76
    ģ
    -1.67
    İ
    -1.58
    ounce
    -1.57
    oving
    -1.51
    ĨĴ
    -1.50
    ]{};
    -1.48
    nis
    -1.46
    ĻĤ
    -1.45
     breeze
    -1.44
    POSITIVE LOGITS
    àµ
    1.38
    Lic
    1.36
    verte
    1.33
    áĢIJ
    1.33
    àµį
    1.33
    llo
    1.30
    leg
    1.30
    OSS
    1.26
    legate
    1.25
     greatest
    1.23
    Activations Density 0.955%

    No Known Activations