© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 29441
    Prev
    Next
    INDEX
    Explanations

    the word "is" in various forms or 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/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
    410
    +0.14
    0.7%
    148
    +0.12
    0.7%
    214
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    426
    +0.14
    0.01
    448
    +0.12
    0.01
    153
    +0.12
    0.01
    Negative Logits
    lam
    -1.56
     prosper
    -1.53
    unnumbered
    -1.42
    www
    -1.40
     she
    -1.36
    lands
    -1.35
    ż
    -1.34
    Enter
    -1.33
    arden
    -1.32
    }{-
    -1.29
    POSITIVE LOGITS
    ²
    3.57
    ¾
    3.55
    ¥
    3.55
    Ĥ¬
    3.38
    ¬
    3.38
    ·
    3.31
    °
    3.28
    Īĺ
    3.28
    ĸ
    3.28
    »¿
    3.27
    Activations Density 1.160%

    No Known Activations