© 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. 22692
    Prev
    Next
    INDEX
    Explanations

    the term "present" in various contexts

    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
    179
    +0.12
    0.7%
    159
    +0.12
    0.7%
    167
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    179
    +0.12
    0.02
    272
    +0.12
    0.02
    335
    +0.12
    0.02
    Negative Logits
    ¥
    -2.34
    «
    -2.32
    ®
    -2.00
    ¬
    -1.91
    ł
    -1.90
    ĵ
    -1.84
    Ĩ
    -1.75
    Ł
    -1.75
    º
    -1.74
    ª
    -1.73
    POSITIVE LOGITS
    iginally
    1.35
     Raz
    1.35
    {%
    1.31
     APC
    1.31
    ipore
    1.30
     Bras
    1.28
    wards
    1.28
    gery
    1.28
     Secure
    1.27
     upright
    1.27
    Activations Density 0.046%

    No Known Activations