© 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. 25949
    Prev
    Next
    INDEX
    Explanations

    chemical compounds, specifically imides

    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
    433
    +0.15
    0.9%
    306
    +0.13
    0.8%
    361
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    433
    +0.15
    0.01
    361
    +0.13
    0.01
    24
    +0.12
    0.01
    Negative Logits
    ij
    -2.25
    ¿½
    -2.18
    Ĥ¬
    -2.16
    Ķ
    -2.13
    ©
    -2.09
    Ĵ
    -1.98
    ´
    -1.98
    ĻĤ
    -1.95
    Īĺ
    -1.94
    ¾
    -1.88
    POSITIVE LOGITS
    jax
    1.53
    illo
    1.51
    oft
    1.49
     enhancement
    1.49
    à±ģ
    1.48
    furt
    1.44
    irez
    1.40
    chie
    1.39
    uary
    1.39
    crow
    1.38
    Activations Density 0.011%

    No Known Activations